Search Results for author: Caiming Xiong

Found 351 papers, 176 papers with code

[CASPI] Causal-aware Safe Policy Improvement for Task-oriented Dialogue

no code implementations ACL 2022 Govardana Sachithanandam Ramachandran, Kazuma Hashimoto, Caiming Xiong

Further more we demonstrate sample efficiency, where our method trained only on 20% of the data, are comparable to current state of the art method trained on 100% data on two out of there evaluation metrics.

Dialogue Management Management +1

Few-Shot Intent Classification by Gauging Entailment Relationship Between Utterance and Semantic Label

no code implementations EMNLP (NLP4ConvAI) 2021 Jin Qu, Kazuma Hashimoto, Wenhao Liu, Caiming Xiong, Yingbo Zhou

Compared with DNNC, our proposed method is more efficient in both training and serving since it is based upon the entailment between query utterance and labels instead of all the training examples.

Classification intent-classification +2

DocQueryNet: Value Retrieval with Arbitrary Queries for Form-like Documents

1 code implementation COLING 2022 Mingfei Gao, Le Xue, Chetan Ramaiah, Chen Xing, ran Xu, Caiming Xiong

Unlike previous methods that only address a fixed set of field items, our method predicts target value for an arbitrary query based on the understanding of the layout and semantics of a form.

document understanding Form +3

Simple Data Augmentation with the Mask Token Improves Domain Adaptation for Dialog Act Tagging

no code implementations EMNLP 2020 Semih Yavuz, Kazuma Hashimoto, Wenhao Liu, Nitish Shirish Keskar, Richard Socher, Caiming Xiong

The concept of Dialogue Act (DA) is universal across different task-oriented dialogue domains - the act of {``}request{''} carries the same speaker intention whether it is for restaurant reservation or flight booking.

Data Augmentation Domain Generalization

The Thieves on Sesame Street are Polyglots - Extracting Multilingual Models from Monolingual APIs

no code implementations EMNLP 2020 Nitish Shirish Keskar, Bryan McCann, Caiming Xiong, Richard Socher

Pre-training in natural language processing makes it easier for an adversary with only query access to a victim model to reconstruct a local copy of the victim by training with gibberish input data paired with the victim{'}s labels for that data.

BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset

1 code implementation14 May 2025 Jiuhai Chen, Zhiyang Xu, Xichen Pan, Yushi Hu, Can Qin, Tom Goldstein, Lifu Huang, Tianyi Zhou, Saining Xie, Silvio Savarese, Le Xue, Caiming Xiong, ran Xu

Building on our innovative model design, training recipe, and datasets, we develop BLIP3-o, a suite of state-of-the-art unified multimodal models.

Image Generation

xGen-small Technical Report

no code implementations10 May 2025 Erik Nijkamp, Bo Pang, Egor Pakhomov, Akash Gokul, Jin Qu, Silvio Savarese, Yingbo Zhou, Caiming Xiong

We introduce xGen-small, a family of 4B and 9B Transformer decoder models optimized for long-context applications.

Decoder Math

Scalable Chain of Thoughts via Elastic Reasoning

no code implementations8 May 2025 Yuhui Xu, Hanze Dong, Lei Wang, Doyen Sahoo, Junnan Li, Caiming Xiong

Large reasoning models (LRMs) have achieved remarkable progress on complex tasks by generating extended chains of thought (CoT).

SweRank: Software Issue Localization with Code Ranking

no code implementations7 May 2025 Revanth Gangi Reddy, Tarun Suresh, JaeHyeok Doo, Ye Liu, Xuan Phi Nguyen, Yingbo Zhou, Semih Yavuz, Caiming Xiong, Heng Ji, Shafiq Joty

Software issue localization, the task of identifying the precise code locations (files, classes, or functions) relevant to a natural language issue description (e. g., bug report, feature request), is a critical yet time-consuming aspect of software development.

Descriptive

LZ Penalty: An information-theoretic repetition penalty for autoregressive language models

no code implementations28 Apr 2025 Antonio A. Ginart, Naveen Kodali, Jason Lee, Caiming Xiong, Silvio Savarese, John R. Emmons

We demonstrate the LZ penalty enables state-of-the-art open-source reasoning models to operate with greedy (temperature zero) decoding without loss of capability and without instances of degenerate repetition.

DyMU: Dynamic Merging and Virtual Unmerging for Efficient VLMs

no code implementations23 Apr 2025 Zhenhailong Wang, Senthil Purushwalkam, Caiming Xiong, Silvio Savarese, Heng Ji, ran Xu

Extensive experiments on image and video understanding tasks demonstrate that DyMU can reduce the average visual token count by 32%-85% while achieving comparable performance to full-length models across diverse VLM architectures, including the recently popularized AnyRes-based visual encoders.

Token Reduction Video Understanding

Evaluating Judges as Evaluators: The JETTS Benchmark of LLM-as-Judges as Test-Time Scaling Evaluators

1 code implementation21 Apr 2025 Yilun Zhou, Austin Xu, Peifeng Wang, Caiming Xiong, Shafiq Joty

Scaling test-time computation, or affording a generator large language model (LLM) extra compute during inference, typically employs the help of external non-generative evaluators (i. e., reward models).

Code Generation Instruction Following +3

Generative Frame Sampler for Long Video Understanding

no code implementations12 Mar 2025 Linli Yao, HaoNing Wu, Kun Ouyang, Yuanxing Zhang, Caiming Xiong, Bei Chen, Xu sun, Junnan Li

Despite recent advances in Video Large Language Models (VideoLLMs), effectively understanding long-form videos remains a significant challenge.

Video Understanding

BingoGuard: LLM Content Moderation Tools with Risk Levels

no code implementations9 Mar 2025 Fan Yin, Philippe Laban, Xiangyu Peng, Yilun Zhou, Yixin Mao, Vaibhav Vats, Linnea Ross, Divyansh Agarwal, Caiming Xiong, Chien-Sheng Wu

Using this framework, we create BingoGuardTrain, a training dataset with 54, 897 examples covering a variety of topics, response severity, styles, and BingoGuardTest, a test set with 988 examples explicitly labeled based on our severity rubrics that enables fine-grained analysis on model behaviors on different severity levels.

A Survey on Post-training of Large Language Models

no code implementations8 Mar 2025 Guiyao Tie, Zeli Zhao, Dingjie Song, Fuyang Wei, Rong Zhou, Yurou Dai, Wen Yin, Zhejian Yang, Jiangyue Yan, Yao Su, Zhenhan Dai, Yifeng Xie, Yihan Cao, Lichao Sun, Pan Zhou, Lifang He, Hechang Chen, Yu Zhang, Qingsong Wen, Tianming Liu, Neil Zhenqiang Gong, Jiliang Tang, Caiming Xiong, Heng Ji, Philip S. Yu, Jianfeng Gao

The emergence of Large Language Models (LLMs) has fundamentally transformed natural language processing, making them indispensable across domains ranging from conversational systems to scientific exploration.

Survey

Reward Models Identify Consistency, Not Causality

no code implementations20 Feb 2025 Yuhui Xu, Hanze Dong, Lei Wang, Caiming Xiong, Junnan Li

Reward models (RMs) play a crucial role in aligning large language models (LLMs) with human preferences and enhancing reasoning quality.

CLOVER: A Test Case Generation Benchmark with Coverage, Long-Context, and Verification

no code implementations12 Feb 2025 Jiacheng Xu, Bo Pang, Jin Qu, Hiroaki Hayashi, Caiming Xiong, Yingbo Zhou

Software testing is a critical aspect of software development, yet generating test cases remains a routine task for engineers.

16k 4k +1

BOLT: Bootstrap Long Chain-of-Thought in Language Models without Distillation

no code implementations6 Feb 2025 Bo Pang, Hanze Dong, Jiacheng Xu, Silvio Savarese, Yingbo Zhou, Caiming Xiong

This paper introduces a novel approach to enable LLM's LongCoT capacity without distillation from o1-like models or expensive human annotations, where we bootstrap LongCoT (BOLT) from a standard instruct model.

In-Context Learning Knowledge Distillation +1

Reward-Guided Speculative Decoding for Efficient LLM Reasoning

no code implementations31 Jan 2025 Baohao Liao, Yuhui Xu, Hanze Dong, Junnan Li, Christof Monz, Silvio Savarese, Doyen Sahoo, Caiming Xiong

We introduce Reward-Guided Speculative Decoding (RSD), a novel framework aimed at improving the efficiency of inference in large language models (LLMs).

Demystifying Domain-adaptive Post-training for Financial LLMs

1 code implementation9 Jan 2025 Zixuan Ke, Yifei Ming, Xuan-Phi Nguyen, Caiming Xiong, Shafiq Joty

Domain-adaptive post-training of large language models (LLMs) has emerged as a promising approach for specialized domains such as medicine and finance.

Continual Pretraining Domain Adaptation +1

Unanswerability Evaluation for Retrieval Augmented Generation

no code implementations16 Dec 2024 Xiangyu Peng, Prafulla Kumar Choubey, Caiming Xiong, Chien-Sheng Wu

Existing evaluation frameworks for retrieval-augmented generation (RAG) systems focus on answerable queries, but they overlook the importance of appropriately rejecting unanswerable requests.

RAG Retrieval

GReaTer: Gradients over Reasoning Makes Smaller Language Models Strong Prompt Optimizers

1 code implementation12 Dec 2024 Sarkar Snigdha Sarathi Das, Ryo Kamoi, Bo Pang, Yusen Zhang, Caiming Xiong, Rui Zhang

The effectiveness of large language models (LLMs) is closely tied to the design of prompts, making prompt optimization essential for enhancing their performance across a wide range of tasks.

GSM8K Prompt Engineering

AgentTrek: Agent Trajectory Synthesis via Guiding Replay with Web Tutorials

no code implementations12 Dec 2024 Yiheng Xu, Dunjie Lu, Zhennan Shen, Junli Wang, Zekun Wang, Yuchen Mao, Caiming Xiong, Tao Yu

This work underscores the potential of guided replay with web tutorials as a viable strategy for large-scale GUI agent training, paving the way for more capable and autonomous digital agents.

Language Modeling Language Modelling

ViUniT: Visual Unit Tests for More Robust Visual Programming

no code implementations12 Dec 2024 Artemis Panagopoulou, Honglu Zhou, Silvio Savarese, Caiming Xiong, Chris Callison-Burch, Mark Yatskar, Juan Carlos Niebles

In our framework, a unit test is represented as a novel image and answer pair meant to verify the logical correctness of a program produced for a given query.

Image Generation Image-text matching +4

SiReRAG: Indexing Similar and Related Information for Multihop Reasoning

no code implementations9 Dec 2024 Nan Zhang, Prafulla Kumar Choubey, Alexander Fabbri, Gabriel Bernadett-Shapiro, Rui Zhang, Prasenjit Mitra, Caiming Xiong, Chien-Sheng Wu

On the similarity side, we follow existing work and explore some variances to construct a similarity tree based on recursive summarization.

RAG Reranking +3

TACO: Learning Multi-modal Action Models with Synthetic Chains-of-Thought-and-Action

1 code implementation7 Dec 2024 Zixian Ma, JianGuo Zhang, Zhiwei Liu, Jieyu Zhang, Juntao Tan, Manli Shu, Juan Carlos Niebles, Shelby Heinecke, Huan Wang, Caiming Xiong, Ranjay Krishna, Silvio Savarese

While open-source multi-modal language models perform well on simple question answering tasks, they often fail on complex questions that require multiple capabilities, such as fine-grained recognition, visual grounding, and reasoning, and that demand multi-step solutions.

Depth Estimation Mathematical Reasoning +4

CodeXEmbed: A Generalist Embedding Model Family for Multiligual and Multi-task Code Retrieval

no code implementations19 Nov 2024 Ye Liu, Rui Meng, Shafiq Joty, Silvio Savarese, Caiming Xiong, Yingbo Zhou, Semih Yavuz

This gap leaves existing models unable to effectively capture the diversity of programming languages and tasks across different domains, highlighting the need for more focused research in code retrieval.

Diversity Natural Language Queries +2

PerfCodeGen: Improving Performance of LLM Generated Code with Execution Feedback

1 code implementation18 Nov 2024 Yun Peng, Akhilesh Deepak Gotmare, Michael Lyu, Caiming Xiong, Silvio Savarese, Doyen Sahoo

Large Language Models (LLMs) are widely adopted for assisting in software development tasks, yet their performance evaluations have narrowly focused on the functional correctness of generated code.

HumanEval mbpp

BLIP3-KALE: Knowledge Augmented Large-Scale Dense Captions

no code implementations12 Nov 2024 Anas Awadalla, Le Xue, Manli Shu, An Yan, Jun Wang, Senthil Purushwalkam, Sheng Shen, Hannah Lee, Oscar Lo, Jae Sung Park, Etash Guha, Silvio Savarese, Ludwig Schmidt, Yejin Choi, Caiming Xiong, ran Xu

We introduce BLIP3-KALE, a dataset of 218 million image-text pairs that bridges the gap between descriptive synthetic captions and factual web-scale alt-text.

Descriptive Image Captioning

Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows

no code implementations12 Nov 2024 Fangyu Lei, Jixuan Chen, Yuxiao Ye, Ruisheng Cao, Dongchan Shin, Hongjin Su, Zhaoqing Suo, Hongcheng Gao, Wenjing Hu, Pengcheng Yin, Victor Zhong, Caiming Xiong, Ruoxi Sun, Qian Liu, Sida Wang, Tao Yu

Real-world enterprise text-to-SQL workflows often involve complex cloud or local data across various database systems, multiple SQL queries in various dialects, and diverse operations from data transformation to analytics.

Code Generation Text-To-SQL

CodeTree: Agent-guided Tree Search for Code Generation with Large Language Models

no code implementations7 Nov 2024 Jierui Li, Hung Le, Yingbo Zhou, Caiming Xiong, Silvio Savarese, Doyen Sahoo

We comprehensively evaluated CodeTree on 7 code generation benchmarks and demonstrated the significant performance gains of CodeTree against strong baselines.

Code Generation Decision Making +2

Language Models are Hidden Reasoners: Unlocking Latent Reasoning Capabilities via Self-Rewarding

1 code implementation6 Nov 2024 Haolin Chen, Yihao Feng, Zuxin Liu, Weiran Yao, Akshara Prabhakar, Shelby Heinecke, Ricky Ho, Phil Mui, Silvio Savarese, Caiming Xiong, Huan Wang

Large language models (LLMs) have shown impressive capabilities, but still struggle with complex reasoning tasks requiring multiple steps.

ARC GSM8K

CRMArena: Understanding the Capacity of LLM Agents to Perform Professional CRM Tasks in Realistic Environments

1 code implementation4 Nov 2024 Kung-Hsiang Huang, Akshara Prabhakar, Sidharth Dhawan, Yixin Mao, Huan Wang, Silvio Savarese, Caiming Xiong, Philippe Laban, Chien-Sheng Wu

Customer Relationship Management (CRM) systems are vital for modern enterprises, providing a foundation for managing customer interactions and data.

JudgeRank: Leveraging Large Language Models for Reasoning-Intensive Reranking

no code implementations31 Oct 2024 Tong Niu, Shafiq Joty, Ye Liu, Caiming Xiong, Yingbo Zhou, Semih Yavuz

Accurate document retrieval is crucial for the success of retrieval-augmented generation (RAG) applications, including open-domain question answering and code completion.

Code Completion Open-Domain Question Answering +4

Asynchronous Tool Usage for Real-Time Agents

no code implementations28 Oct 2024 Antonio A. Ginart, Naveen Kodali, Jason Lee, Caiming Xiong, Silvio Savarese, John Emmons

While frontier large language models (LLMs) are capable tool-using agents, current AI systems still operate in a strict turn-based fashion, oblivious to passage of time.

Automatic Speech Recognition speech-recognition +3

PRACT: Optimizing Principled Reasoning and Acting of LLM Agent

no code implementations24 Oct 2024 Zhiwei Liu, Weiran Yao, JianGuo Zhang, Rithesh Murthy, Liangwei Yang, Zuxin Liu, Tian Lan, Ming Zhu, Juntao Tan, Shirley Kokane, Thai Hoang, Juan Carlos Niebles, Shelby Heinecke, Huan Wang, Silvio Savarese, Caiming Xiong

We introduce the Principled Reasoning and Acting (PRAct) framework, a novel method for learning and enforcing action principles from trajectory data.

xGen-MM-Vid (BLIP-3-Video): You Only Need 32 Tokens to Represent a Video Even in VLMs

no code implementations21 Oct 2024 Michael S. Ryoo, Honglu Zhou, Shrikant Kendre, Can Qin, Le Xue, Manli Shu, Silvio Savarese, ran Xu, Caiming Xiong, Juan Carlos Niebles

We present xGen-MM-Vid (BLIP-3-Video): a multimodal language model for videos, particularly designed to efficiently capture temporal information over multiple frames.

Language Modeling Language Modelling +2

Do RAG Systems Cover What Matters? Evaluating and Optimizing Responses with Sub-Question Coverage

1 code implementation20 Oct 2024 Kaige Xie, Philippe Laban, Prafulla Kumar Choubey, Caiming Xiong, Chien-Sheng Wu

Using this categorization, we introduce a fine-grained evaluation protocol that provides insights into the retrieval and generation characteristics of RAG systems, including three commercial generative answer engines: You. com, Perplexity AI, and Bing Chat.

Answer Generation RAG +1

Trust but Verify: Programmatic VLM Evaluation in the Wild

no code implementations17 Oct 2024 Viraj Prabhu, Senthil Purushwalkam, An Yan, Caiming Xiong, ran Xu

Next, to evaluate free-form model responses to queries in PROVE, we propose a programmatic evaluation strategy that measures both the helpfulness and truthfulness of a response within a unified scene graph-based framework.

Benchmarking Language Modelling +1

GIFT-Eval: A Benchmark For General Time Series Forecasting Model Evaluation

1 code implementation14 Oct 2024 Taha Aksu, Gerald Woo, Juncheng Liu, Xu Liu, Chenghao Liu, Silvio Savarese, Caiming Xiong, Doyen Sahoo

Additionally, we provide a comprehensive analysis of 17 baselines, which includes statistical models, deep learning models, and foundation models.

Time Series Time Series Forecasting

Automatic Curriculum Expert Iteration for Reliable LLM Reasoning

1 code implementation10 Oct 2024 Zirui Zhao, Hanze Dong, Amrita Saha, Caiming Xiong, Doyen Sahoo

To mitigate hallucination and laziness in reasoning tasks, we propose Automatic Curriculum Expert Iteration (Auto-CEI) to enhance LLM reasoning and align responses to the model's capabilities--assertively answering within its limits and declining when tasks exceed them.

Hallucination Logical Reasoning

MathHay: An Automated Benchmark for Long-Context Mathematical Reasoning in LLMs

no code implementations7 Oct 2024 Lei Wang, Shan Dong, Yuhui Xu, Hanze Dong, Yalu Wang, Amrita Saha, Ee-Peng Lim, Caiming Xiong, Doyen Sahoo

Although some recent benchmarks have been developed to evaluate the long-context capabilities of LLMs, there is a lack of benchmarks evaluating the mathematical reasoning abilities of LLMs over long contexts, which is crucial for LLMs' application in real-world scenarios.

Information Retrieval Mathematical Reasoning

ReGenesis: LLMs can Grow into Reasoning Generalists via Self-Improvement

no code implementations3 Oct 2024 Xiangyu Peng, Congying Xia, Xinyi Yang, Caiming Xiong, Chien-Sheng Wu, Chen Xing

We show that ReGenesis achieves superior performance on all in-domain and OOD settings tested compared to existing methods.

FaithEval: Can Your Language Model Stay Faithful to Context, Even If "The Moon is Made of Marshmallows"

1 code implementation30 Sep 2024 Yifei Ming, Senthil Purushwalkam, Shrey Pandit, Zixuan Ke, Xuan-Phi Nguyen, Caiming Xiong, Shafiq Joty

Ensuring faithfulness to context in large language models (LLMs) and retrieval-augmented generation (RAG) systems is crucial for reliable deployment in real-world applications, as incorrect or unsupported information can erode user trust.

counterfactual Hallucination +4

Direct Judgement Preference Optimization

no code implementations23 Sep 2024 Peifeng Wang, Austin Xu, Yilun Zhou, Caiming Xiong, Shafiq Joty

Auto-evaluation is crucial for assessing response quality and offering feedback for model development.

xLAM: A Family of Large Action Models to Empower AI Agent Systems

1 code implementation5 Sep 2024 JianGuo Zhang, Tian Lan, Ming Zhu, Zuxin Liu, Thai Hoang, Shirley Kokane, Weiran Yao, Juntao Tan, Akshara Prabhakar, Haolin Chen, Zhiwei Liu, Yihao Feng, Tulika Awalgaonkar, Rithesh Murthy, Eric Hu, Zeyuan Chen, ran Xu, Juan Carlos Niebles, Shelby Heinecke, Huan Wang, Silvio Savarese, Caiming Xiong

By releasing the xLAM series, we aim to advance the performance of open-source LLMs for autonomous AI agents, potentially accelerating progress and democratizing access to high-performance models for agent tasks.

AI Agent

Diversity Empowers Intelligence: Integrating Expertise of Software Engineering Agents

no code implementations13 Aug 2024 Kexun Zhang, Weiran Yao, Zuxin Liu, Yihao Feng, Zhiwei Liu, Rithesh Murthy, Tian Lan, Lei LI, Renze Lou, Jiacheng Xu, Bo Pang, Yingbo Zhou, Shelby Heinecke, Silvio Savarese, Huan Wang, Caiming Xiong

For instance, a group of open-source SWE agents, with a maximum individual resolve rate of 27. 3% on SWE-Bench Lite, can achieve a 34. 3% resolve rate with DEI, making a 25% improvement and beating most closed-source solutions.

Diversity Language Modeling +2

Enabling High Data Throughput Reinforcement Learning on GPUs: A Domain Agnostic Framework for Data-Driven Scientific Research

no code implementations1 Aug 2024 Tian Lan, Huan Wang, Caiming Xiong, Silvio Savarese

We introduce WarpSci, a domain agnostic framework designed to overcome crucial system bottlenecks encountered in the application of reinforcement learning to intricate environments with vast datasets featuring high-dimensional observation or action spaces.

reinforcement-learning

Personalized Multi-task Training for Recommender System

no code implementations31 Jul 2024 Liangwei Yang, Zhiwei Liu, JianGuo Zhang, Rithesh Murthy, Shelby Heinecke, Huan Wang, Caiming Xiong, Philip S. Yu

In the vast landscape of internet information, recommender systems (RecSys) have become essential for guiding users through a sea of choices aligned with their preferences.

Multi-Task Learning Recommendation Systems +1

ThinK: Thinner Key Cache by Query-Driven Pruning

no code implementations30 Jul 2024 Yuhui Xu, Zhanming Jie, Hanze Dong, Lei Wang, Xudong Lu, Aojun Zhou, Amrita Saha, Caiming Xiong, Doyen Sahoo

Large Language Models (LLMs) have revolutionized the field of natural language processing, achieving unprecedented performance across a variety of applications.

Quantization

Shared Imagination: LLMs Hallucinate Alike

no code implementations23 Jul 2024 Yilun Zhou, Caiming Xiong, Silvio Savarese, Chien-Sheng Wu

In this paper, we propose a novel setting, imaginary question answering (IQA), to better understand model similarity.

Hallucination Question Answering

Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows?

1 code implementation15 Jul 2024 Ruisheng Cao, Fangyu Lei, Haoyuan Wu, Jixuan Chen, Yeqiao Fu, Hongcheng Gao, Xinzhuang Xiong, Hanchong Zhang, Yuchen Mao, Wenjing Hu, Tianbao Xie, Hongshen Xu, Danyang Zhang, Sida Wang, Ruoxi Sun, Pengcheng Yin, Caiming Xiong, Ansong Ni, Qian Liu, Victor Zhong, Lu Chen, Kai Yu, Tao Yu

These tasks, derived from real-world use cases, evaluate the ability of a multimodal agent to perform data-related tasks by writing code and managing the GUI in enterprise data software systems.

Code Generation

Summary of a Haystack: A Challenge to Long-Context LLMs and RAG Systems

1 code implementation1 Jul 2024 Philippe Laban, Alexander R. Fabbri, Caiming Xiong, Chien-Sheng Wu

The "Summary of a Haystack" (SummHay) task then requires a system to process the Haystack and generate, given a query, a summary that identifies the relevant insights and precisely cites the source documents.

RAG

INDICT: Code Generation with Internal Dialogues of Critiques for Both Security and Helpfulness

1 code implementation23 Jun 2024 Hung Le, Yingbo Zhou, Caiming Xiong, Silvio Savarese, Doyen Sahoo

In this work, we introduce INDICT: a new framework that empowers LLMs with Internal Dialogues of Critiques for both safety and helpfulness guidance.

Code Generation Navigate

MINT-1T: Scaling Open-Source Multimodal Data by 10x: A Multimodal Dataset with One Trillion Tokens

1 code implementation17 Jun 2024 Anas Awadalla, Le Xue, Oscar Lo, Manli Shu, Hannah Lee, Etash Kumar Guha, Matt Jordan, Sheng Shen, Mohamed Awadalla, Silvio Savarese, Caiming Xiong, ran Xu, Yejin Choi, Ludwig Schmidt

Multimodal interleaved datasets featuring free-form interleaved sequences of images and text are crucial for training frontier large multimodal models (LMMs).

MobileAIBench: Benchmarking LLMs and LMMs for On-Device Use Cases

no code implementations12 Jun 2024 Rithesh Murthy, Liangwei Yang, Juntao Tan, Tulika Manoj Awalgaonkar, Yilun Zhou, Shelby Heinecke, Sachin Desai, Jason Wu, ran Xu, Sarah Tan, JianGuo Zhang, Zhiwei Liu, Shirley Kokane, Zuxin Liu, Ming Zhu, Huan Wang, Caiming Xiong, Silvio Savarese

The deployment of Large Language Models (LLMs) and Large Multimodal Models (LMMs) on mobile devices has gained significant attention due to the benefits of enhanced privacy, stability, and personalization.

Benchmarking Model Compression +1

RLHF Workflow: From Reward Modeling to Online RLHF

3 code implementations13 May 2024 Hanze Dong, Wei Xiong, Bo Pang, Haoxiang Wang, Han Zhao, Yingbo Zhou, Nan Jiang, Doyen Sahoo, Caiming Xiong, Tong Zhang

We present the workflow of Online Iterative Reinforcement Learning from Human Feedback (RLHF) in this technical report, which is widely reported to outperform its offline counterpart by a large margin in the recent large language model (LLM) literature.

Chatbot HumanEval +3

OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments

1 code implementation11 Apr 2024 Tianbao Xie, Danyang Zhang, Jixuan Chen, Xiaochuan Li, Siheng Zhao, Ruisheng Cao, Toh Jing Hua, Zhoujun Cheng, Dongchan Shin, Fangyu Lei, Yitao Liu, Yiheng Xu, Shuyan Zhou, Silvio Savarese, Caiming Xiong, Victor Zhong, Tao Yu

Autonomous agents that accomplish complex computer tasks with minimal human interventions have the potential to transform human-computer interaction, significantly enhancing accessibility and productivity.

Benchmarking

What Are We Measuring When We Evaluate Large Vision-Language Models? An Analysis of Latent Factors and Biases

1 code implementation3 Apr 2024 Anthony Meng Huat Tiong, Junqi Zhao, Boyang Li, Junnan Li, Steven C. H. Hoi, Caiming Xiong

Vision-language (VL) models, pretrained on colossal image-text datasets, have attained broad VL competence that is difficult to evaluate.

Transfer Learning

How Much are Large Language Models Contaminated? A Comprehensive Survey and the LLMSanitize Library

1 code implementation31 Mar 2024 Mathieu Ravaut, Bosheng Ding, Fangkai Jiao, Hailin Chen, Xingxuan Li, Ruochen Zhao, Chengwei Qin, Caiming Xiong, Shafiq Joty

With the rise of Large Language Models (LLMs) in recent years, abundant new opportunities are emerging, but also new challenges, among which contamination is quickly becoming critical.

Question Answering

FOFO: A Benchmark to Evaluate LLMs' Format-Following Capability

1 code implementation28 Feb 2024 Congying Xia, Chen Xing, Jiangshu Du, Xinyi Yang, Yihao Feng, ran Xu, Wenpeng Yin, Caiming Xiong

This paper presents FoFo, a pioneering benchmark for evaluating large language models' (LLMs) ability to follow complex, domain-specific formats, a crucial yet underexamined capability for their application as AI agents.

AgentLite: A Lightweight Library for Building and Advancing Task-Oriented LLM Agent System

1 code implementation23 Feb 2024 Zhiwei Liu, Weiran Yao, JianGuo Zhang, Liangwei Yang, Zuxin Liu, Juntao Tan, Prafulla K. Choubey, Tian Lan, Jason Wu, Huan Wang, Shelby Heinecke, Caiming Xiong, Silvio Savarese

Thus, we open-source a new AI agent library, AgentLite, which simplifies this process by offering a lightweight, user-friendly platform for innovating LLM agent reasoning, architectures, and applications with ease.

AI Agent

AgentOhana: Design Unified Data and Training Pipeline for Effective Agent Learning

2 code implementations23 Feb 2024 JianGuo Zhang, Tian Lan, Rithesh Murthy, Zhiwei Liu, Weiran Yao, Ming Zhu, Juntao Tan, Thai Hoang, Zuxin Liu, Liangwei Yang, Yihao Feng, Shirley Kokane, Tulika Awalgaonkar, Juan Carlos Niebles, Silvio Savarese, Shelby Heinecke, Huan Wang, Caiming Xiong

It meticulously standardizes and unifies these trajectories into a consistent format, streamlining the creation of a generic data loader optimized for agent training.

Text2Data: Low-Resource Data Generation with Textual Control

no code implementations8 Feb 2024 Shiyu Wang, Yihao Feng, Tian Lan, Ning Yu, Yu Bai, ran Xu, Huan Wang, Caiming Xiong, Silvio Savarese

Natural language serves as a common and straightforward signal for humans to interact seamlessly with machines.

Audio Synthesis Time Series

Unified Training of Universal Time Series Forecasting Transformers

2 code implementations4 Feb 2024 Gerald Woo, Chenghao Liu, Akshat Kumar, Caiming Xiong, Silvio Savarese, Doyen Sahoo

Deep learning for time series forecasting has traditionally operated within a one-model-per-dataset framework, limiting its potential to leverage the game-changing impact of large pre-trained models.

Time Series Time Series Forecasting

Causal Layering via Conditional Entropy

no code implementations19 Jan 2024 Itai Feigenbaum, Devansh Arpit, Huan Wang, Shelby Heinecke, Juan Carlos Niebles, Weiran Yao, Caiming Xiong, Silvio Savarese

Under appropriate assumptions and conditioning, we can separate the sources or sinks from the remainder of the nodes by comparing their conditional entropy to the unconditional entropy of their noise.

Causal Discovery

Editing Arbitrary Propositions in LLMs without Subject Labels

no code implementations15 Jan 2024 Itai Feigenbaum, Devansh Arpit, Huan Wang, Shelby Heinecke, Juan Carlos Niebles, Weiran Yao, Caiming Xiong, Silvio Savarese

On datasets of binary propositions derived from the CounterFact dataset, we show that our method -- without access to subject labels -- performs close to state-of-the-art L\&E methods which has access subject labels.

Language Modelling Large Language Model +1

Moonshot: Towards Controllable Video Generation and Editing with Multimodal Conditions

2 code implementations3 Jan 2024 David Junhao Zhang, Dongxu Li, Hung Le, Mike Zheng Shou, Caiming Xiong, Doyen Sahoo

This work presents Moonshot, a new video generation model that conditions simultaneously on multimodal inputs of image and text.

Image Animation Video Editing +1

X-InstructBLIP: A Framework for aligning X-Modal instruction-aware representations to LLMs and Emergent Cross-modal Reasoning

2 code implementations30 Nov 2023 Artemis Panagopoulou, Le Xue, Ning Yu, Junnan Li, Dongxu Li, Shafiq Joty, ran Xu, Silvio Savarese, Caiming Xiong, Juan Carlos Niebles

To enable this framework, we devise a scalable pipeline that automatically generates high-quality, instruction-tuning datasets from readily available captioning data across different modalities, and contribute 24K QA data for audio and 250K QA data for 3D.

Visual Reasoning

Diffusion Model Alignment Using Direct Preference Optimization

2 code implementations CVPR 2024 Bram Wallace, Meihua Dang, Rafael Rafailov, Linqi Zhou, Aaron Lou, Senthil Purushwalkam, Stefano Ermon, Caiming Xiong, Shafiq Joty, Nikhil Naik

Large language models (LLMs) are fine-tuned using human comparison data with Reinforcement Learning from Human Feedback (RLHF) methods to make them better aligned with users' preferences.

model

Lexical Repetitions Lead to Rote Learning: Unveiling the Impact of Lexical Overlap in Train and Test Reference Summaries

no code implementations15 Nov 2023 Prafulla Kumar Choubey, Alexander R. Fabbri, Caiming Xiong, Chien-Sheng Wu

Ideal summarization models should generalize to novel summary-worthy content without remembering reference training summaries by rote.

Are You Sure? Challenging LLMs Leads to Performance Drops in The FlipFlop Experiment

no code implementations14 Nov 2023 Philippe Laban, Lidiya Murakhovs'ka, Caiming Xiong, Chien-Sheng Wu

The interactive nature of Large Language Models (LLMs) theoretically allows models to refine and improve their answers, yet systematic analysis of the multi-turn behavior of LLMs remains limited.

Fair Abstractive Summarization of Diverse Perspectives

1 code implementation14 Nov 2023 Yusen Zhang, Nan Zhang, Yixin Liu, Alexander Fabbri, Junru Liu, Ryo Kamoi, Xiaoxin Lu, Caiming Xiong, Jieyu Zhao, Dragomir Radev, Kathleen McKeown, Rui Zhang

However, current work in summarization metrics and Large Language Models (LLMs) evaluation has not explored fair abstractive summarization.

Abstractive Text Summarization Fairness

How Do Transformers Learn In-Context Beyond Simple Functions? A Case Study on Learning with Representations

no code implementations16 Oct 2023 Tianyu Guo, Wei Hu, Song Mei, Huan Wang, Caiming Xiong, Silvio Savarese, Yu Bai

Through extensive probing and a new pasting experiment, we further reveal several mechanisms within the trained transformers, such as concrete copying behaviors on both the inputs and the representations, linear ICL capability of the upper layers alone, and a post-ICL representation selection mechanism in a harder mixture setting.

In-Context Learning

OpenAgents: An Open Platform for Language Agents in the Wild

2 code implementations16 Oct 2023 Tianbao Xie, Fan Zhou, Zhoujun Cheng, Peng Shi, Luoxuan Weng, Yitao Liu, Toh Jing Hua, Junning Zhao, Qian Liu, Che Liu, Leo Z. Liu, Yiheng Xu, Hongjin Su, Dongchan Shin, Caiming Xiong, Tao Yu

Language agents show potential in being capable of utilizing natural language for varied and intricate tasks in diverse environments, particularly when built upon large language models (LLMs).

2D Object Detection

Lemur: Harmonizing Natural Language and Code for Language Agents

1 code implementation10 Oct 2023 Yiheng Xu, Hongjin Su, Chen Xing, Boyu Mi, Qian Liu, Weijia Shi, Binyuan Hui, Fan Zhou, Yitao Liu, Tianbao Xie, Zhoujun Cheng, Siheng Zhao, Lingpeng Kong, Bailin Wang, Caiming Xiong, Tao Yu

We introduce Lemur and Lemur-Chat, openly accessible language models optimized for both natural language and coding capabilities to serve as the backbone of versatile language agents.

L2CEval: Evaluating Language-to-Code Generation Capabilities of Large Language Models

no code implementations29 Sep 2023 Ansong Ni, Pengcheng Yin, Yilun Zhao, Martin Riddell, Troy Feng, Rui Shen, Stephen Yin, Ye Liu, Semih Yavuz, Caiming Xiong, Shafiq Joty, Yingbo Zhou, Dragomir Radev, Arman Cohan

Recently, large language models (LLMs), especially those that are pretrained on code, have demonstrated strong capabilities in generating programs from natural language inputs in a few-shot or even zero-shot manner.

Code Generation Math +1

Beyond the Chat: Executable and Verifiable Text-Editing with LLMs

no code implementations27 Sep 2023 Philippe Laban, Jesse Vig, Marti A. Hearst, Caiming Xiong, Chien-Sheng Wu

Conversational interfaces powered by Large Language Models (LLMs) have recently become a popular way to obtain feedback during document editing.

XGen-7B Technical Report

1 code implementation7 Sep 2023 Erik Nijkamp, Tian Xie, Hiroaki Hayashi, Bo Pang, Congying Xia, Chen Xing, Jesse Vig, Semih Yavuz, Philippe Laban, Ben Krause, Senthil Purushwalkam, Tong Niu, Wojciech Kryściński, Lidiya Murakhovs'ka, Prafulla Kumar Choubey, Alex Fabbri, Ye Liu, Rui Meng, Lifu Tu, Meghana Bhat, Chien-Sheng Wu, Silvio Savarese, Yingbo Zhou, Shafiq Joty, Caiming Xiong

Most open-source LLMs, on the other hand, are limited in their ability to support longer sequence lengths, which is a key requirement for many tasks that require inference over an input context.

2k 8k

Enhancing Performance on Seen and Unseen Dialogue Scenarios using Retrieval-Augmented End-to-End Task-Oriented System

no code implementations16 Aug 2023 JianGuo Zhang, Stephen Roller, Kun Qian, Zhiwei Liu, Rui Meng, Shelby Heinecke, Huan Wang, Silvio Savarese, Caiming Xiong

End-to-end task-oriented dialogue (TOD) systems have achieved promising performance by leveraging sophisticated natural language understanding and natural language generation capabilities of pre-trained models.

Natural Language Understanding Retrieval +1

Retroformer: Retrospective Large Language Agents with Policy Gradient Optimization

1 code implementation4 Aug 2023 Weiran Yao, Shelby Heinecke, Juan Carlos Niebles, Zhiwei Liu, Yihao Feng, Le Xue, Rithesh Murthy, Zeyuan Chen, JianGuo Zhang, Devansh Arpit, ran Xu, Phil Mui, Huan Wang, Caiming Xiong, Silvio Savarese

This demonstrates that using policy gradient optimization to improve language agents, for which we believe our work is one of the first, seems promising and can be applied to optimize other models in the agent architecture to enhance agent performances over time.

Language Modelling

DialogStudio: Towards Richest and Most Diverse Unified Dataset Collection for Conversational AI

1 code implementation19 Jul 2023 JianGuo Zhang, Kun Qian, Zhiwei Liu, Shelby Heinecke, Rui Meng, Ye Liu, Zhou Yu, Huan Wang, Silvio Savarese, Caiming Xiong

Despite advancements in conversational AI, language models encounter challenges to handle diverse conversational tasks, and existing dialogue dataset collections often lack diversity and comprehensiveness.

Conversational Recommendation Diversity +4

Sample-Efficient Learning of POMDPs with Multiple Observations In Hindsight

no code implementations6 Jul 2023 Jiacheng Guo, Minshuo Chen, Huan Wang, Caiming Xiong, Mengdi Wang, Yu Bai

This paper studies the sample-efficiency of learning in Partially Observable Markov Decision Processes (POMDPs), a challenging problem in reinforcement learning that is known to be exponentially hard in the worst-case.

Did You Read the Instructions? Rethinking the Effectiveness of Task Definitions in Instruction Learning

1 code implementation1 Jun 2023 Fan Yin, Jesse Vig, Philippe Laban, Shafiq Joty, Caiming Xiong, Chien-Sheng Jason Wu

Large language models (LLMs) have shown impressive performance in following natural language instructions to solve unseen tasks.

SWiPE: A Dataset for Document-Level Simplification of Wikipedia Pages

1 code implementation30 May 2023 Philippe Laban, Jesse Vig, Wojciech Kryscinski, Shafiq Joty, Caiming Xiong, Chien-Sheng Wu

Text simplification research has mostly focused on sentence-level simplification, even though many desirable edits - such as adding relevant background information or reordering content - may require document-level context.

Sentence Text Simplification

LLMs as Factual Reasoners: Insights from Existing Benchmarks and Beyond

1 code implementation23 May 2023 Philippe Laban, Wojciech Kryściński, Divyansh Agarwal, Alexander R. Fabbri, Caiming Xiong, Shafiq Joty, Chien-Sheng Wu

To address this, we propose a new protocol for inconsistency detection benchmark creation and implement it in a 10-domain benchmark called SummEdits.

Misinformation

Zero-shot Item-based Recommendation via Multi-task Product Knowledge Graph Pre-Training

no code implementations12 May 2023 Ziwei Fan, Zhiwei Liu, Shelby Heinecke, JianGuo Zhang, Huan Wang, Caiming Xiong, Philip S. Yu

This paper presents a novel paradigm for the Zero-Shot Item-based Recommendation (ZSIR) task, which pre-trains a model on product knowledge graph (PKG) to refine the item features from PLMs.

Recommendation Systems

HPE:Answering Complex Questions over Text by Hybrid Question Parsing and Execution

no code implementations12 May 2023 Ye Liu, Semih Yavuz, Rui Meng, Dragomir Radev, Caiming Xiong, Yingbo Zhou

It comprises two central pillars: (1) We parse the question of varying complexity into an intermediate representation, named H-expression, which is composed of simple questions as the primitives and symbolic operations representing the relationships among them; (2) To execute the resulting H-expressions, we design a hybrid executor, which integrates the deterministic rules to translate the symbolic operations with a drop-in neural reader network to answer each decomposed simple question.

Knowledge Graphs Question Answering +1

CodeGen2: Lessons for Training LLMs on Programming and Natural Languages

2 code implementations3 May 2023 Erik Nijkamp, Hiroaki Hayashi, Caiming Xiong, Silvio Savarese, Yingbo Zhou

In this study, we attempt to render the training of LLMs for program synthesis more efficient by unifying four key components: (1) model architectures, (2) learning methods, (3) infill sampling, and, (4) data distributions.

Causal Language Modeling Decoder +4

Efficiently Aligned Cross-Lingual Transfer Learning for Conversational Tasks using Prompt-Tuning

1 code implementation3 Apr 2023 Lifu Tu, Jin Qu, Semih Yavuz, Shafiq Joty, Wenhao Liu, Caiming Xiong, Yingbo Zhou

Our results demonstrate the strong and efficient modeling ability of NLI-based classifiers and the large cross-lingual transfer improvements achieved by our aligned prompts, particularly in few-shot settings.

Cross-Lingual Transfer intent-classification +4

GlueGen: Plug and Play Multi-modal Encoders for X-to-image Generation

1 code implementation ICCV 2023 Can Qin, Ning Yu, Chen Xing, Shu Zhang, Zeyuan Chen, Stefano Ermon, Yun Fu, Caiming Xiong, ran Xu

Empirical results show that GlueNet can be trained efficiently and enables various capabilities beyond previous state-of-the-art models: 1) multilingual language models such as XLM-Roberta can be aligned with existing T2I models, allowing for the generation of high-quality images from captions beyond English; 2) GlueNet can align multi-modal encoders such as AudioCLIP with the Stable Diffusion model, enabling sound-to-image generation; 3) it can also upgrade the current text encoder of the latent diffusion model for challenging case generation.

Decoder Image Generation

On the Unlikelihood of D-Separation

no code implementations10 Mar 2023 Itai Feigenbaum, Huan Wang, Shelby Heinecke, Juan Carlos Niebles, Weiran Yao, Caiming Xiong, Devansh Arpit

We then provide an analytic average case analysis of the PC Algorithm for causal discovery, as well as a variant of the SGS Algorithm we call UniformSGS.

Causal Discovery

Towards Interpretable and Efficient Automatic Reference-Based Summarization Evaluation

1 code implementation7 Mar 2023 Yixin Liu, Alexander R. Fabbri, Yilun Zhao, PengFei Liu, Shafiq Joty, Chien-Sheng Wu, Caiming Xiong, Dragomir Radev

Interpretability and efficiency are two important considerations for the adoption of neural automatic metrics.

A Comprehensive Survey on Pretrained Foundation Models: A History from BERT to ChatGPT

no code implementations18 Feb 2023 Ce Zhou, Qian Li, Chen Li, Jun Yu, Yixin Liu, Guangjing Wang, Kai Zhang, Cheng Ji, Qiben Yan, Lifang He, Hao Peng, JianXin Li, Jia Wu, Ziwei Liu, Pengtao Xie, Caiming Xiong, Jian Pei, Philip S. Yu, Lichao Sun

This study provides a comprehensive review of recent research advancements, challenges, and opportunities for PFMs in text, image, graph, as well as other data modalities.

Graph Learning Language Modelling +1

Designing and Evaluating Interfaces that Highlight News Coverage Diversity Using Discord Questions

no code implementations17 Feb 2023 Philippe Laban, Chien-Sheng Wu, Lidiya Murakhovs'ka, Xiang 'Anthony' Chen, Caiming Xiong

In a second usability study, we developed and implemented a reading exercise with 95 novice news readers to measure exposure to coverage diversity.

Diversity

Improved Online Conformal Prediction via Strongly Adaptive Online Learning

2 code implementations15 Feb 2023 Aadyot Bhatnagar, Huan Wang, Caiming Xiong, Yu Bai

We prove that our methods achieve near-optimal strongly adaptive regret for all interval lengths simultaneously, and approximately valid coverage.

Conformal Prediction Image Classification +5

Lower Bounds for Learning in Revealing POMDPs

no code implementations2 Feb 2023 Fan Chen, Huan Wang, Caiming Xiong, Song Mei, Yu Bai

However, the fundamental limits for learning in revealing POMDPs are much less understood, with existing lower bounds being rather preliminary and having substantial gaps from the current best upper bounds.

Reinforcement Learning (RL)

Hierarchical Point Attention for Indoor 3D Object Detection

no code implementations6 Jan 2023 Manli Shu, Le Xue, Ning Yu, Roberto Martín-Martín, Caiming Xiong, Tom Goldstein, Juan Carlos Niebles, ran Xu

By plugging our proposed modules into the state-of-the-art transformer-based 3D detectors, we improve the previous best results on both benchmarks, with more significant improvements on smaller objects.

3D Object Detection Object +1

Best-$k$ Search Algorithm for Neural Text Generation

no code implementations22 Nov 2022 Jiacheng Xu, Caiming Xiong, Silvio Savarese, Yingbo Zhou

We first investigate the vanilla best-first search (BFS) algorithm and then propose the Best-$k$ Search algorithm.

Diversity Question Generation +3

SPE: Symmetrical Prompt Enhancement for Fact Probing

no code implementations14 Nov 2022 Yiyuan Li, Tong Che, Yezhen Wang, Zhengbao Jiang, Caiming Xiong, Snigdha Chaturvedi

In this work, we propose Symmetrical Prompt Enhancement (SPE), a continuous prompt-based method for factual probing in PLMs that leverages the symmetry of the task by constructing symmetrical prompts for subject and object prediction.

Object Prediction

Improving Factual Consistency in Summarization with Compression-Based Post-Editing

1 code implementation11 Nov 2022 Alexander R. Fabbri, Prafulla Kumar Choubey, Jesse Vig, Chien-Sheng Wu, Caiming Xiong

We propose to use sentence-compression data to train the post-editing model to take a summary with extrinsic entity errors marked with special tokens and output a compressed, well-formed summary with those errors removed.

Informativeness Sentence +1

Uni-Parser: Unified Semantic Parser for Question Answering on Knowledge Base and Database

no code implementations9 Nov 2022 Ye Liu, Semih Yavuz, Rui Meng, Dragomir Radev, Caiming Xiong, Yingbo Zhou

Parsing natural language questions into executable logical forms is a useful and interpretable way to perform question answering on structured data such as knowledge bases (KB) or databases (DB).

Question Answering Semantic Parsing

Model ensemble instead of prompt fusion: a sample-specific knowledge transfer method for few-shot prompt tuning

no code implementations23 Oct 2022 Xiangyu Peng, Chen Xing, Prafulla Kumar Choubey, Chien-Sheng Wu, Caiming Xiong

Through this way, SESoM inherits the superior generalization of model ensemble approaches and simultaneously captures the sample-specific competence of each source prompt.

Transfer Learning

Prompt-Tuning Can Be Much Better Than Fine-Tuning on Cross-lingual Understanding With Multilingual Language Models

2 code implementations22 Oct 2022 Lifu Tu, Caiming Xiong, Yingbo Zhou

Pre-trained multilingual language models show significant performance gains for zero-shot cross-lingual model transfer on a wide range of natural language understanding (NLU) tasks.

Cross-Lingual Transfer Natural Language Understanding +3

Binding Language Models in Symbolic Languages

4 code implementations6 Oct 2022 Zhoujun Cheng, Tianbao Xie, Peng Shi, Chengzu Li, Rahul Nadkarni, Yushi Hu, Caiming Xiong, Dragomir Radev, Mari Ostendorf, Luke Zettlemoyer, Noah A. Smith, Tao Yu

We propose Binder, a training-free neural-symbolic framework that maps the task input to a program, which (1) allows binding a unified API of language model (LM) functionalities to a programming language (e. g., SQL, Python) to extend its grammar coverage and thus tackle more diverse questions, (2) adopts an LM as both the program parser and the underlying model called by the API during execution, and (3) requires only a few in-context exemplar annotations.

Language Modelling Semantic Parsing +1

Generating Negative Samples for Sequential Recommendation

no code implementations7 Aug 2022 Yongjun Chen, Jia Li, Zhiwei Liu, Nitish Shirish Keskar, Huan Wang, Julian McAuley, Caiming Xiong

Due to the dynamics of users' interests and model updates during training, considering randomly sampled items from a user's non-interacted item set as negatives can be uninformative.

Sequential Recommendation

BigIssue: A Realistic Bug Localization Benchmark

no code implementations21 Jul 2022 Paul Kassianik, Erik Nijkamp, Bo Pang, Yingbo Zhou, Caiming Xiong

As machine learning tools progress, the inevitable question arises: How can machine learning help us write better code?

BIG-bench Machine Learning Diversity +1

Policy Optimization for Markov Games: Unified Framework and Faster Convergence

no code implementations6 Jun 2022 Runyu Zhang, Qinghua Liu, Huan Wang, Caiming Xiong, Na Li, Yu Bai

Next, we show that this framework instantiated with the Optimistic Follow-The-Regularized-Leader (OFTRL) algorithm at each state (and smooth value updates) can find an $\mathcal{\widetilde{O}}(T^{-5/6})$ approximate NE in $T$ iterations, and a similar algorithm with slightly modified value update rule achieves a faster $\mathcal{\widetilde{O}}(T^{-1})$ convergence rate.

Multi-agent Reinforcement Learning

MACE: An Efficient Model-Agnostic Framework for Counterfactual Explanation

1 code implementation31 May 2022 Wenzhuo Yang, Jia Li, Caiming Xiong, Steven C. H. Hoi

Counterfactual explanation is an important Explainable AI technique to explain machine learning predictions.

BIG-bench Machine Learning counterfactual +1

Modeling Multi-hop Question Answering as Single Sequence Prediction

no code implementations ACL 2022 Semih Yavuz, Kazuma Hashimoto, Yingbo Zhou, Nitish Shirish Keskar, Caiming Xiong

Fusion-in-decoder (Fid) (Izacard and Grave, 2020) is a generative question answering (QA) model that leverages passage retrieval with a pre-trained transformer and pushed the state of the art on single-hop QA.

Answer Generation Decoder +5

OneAligner: Zero-shot Cross-lingual Transfer with One Rich-Resource Language Pair for Low-Resource Sentence Retrieval

no code implementations Findings (ACL) 2022 Tong Niu, Kazuma Hashimoto, Yingbo Zhou, Caiming Xiong

When finetuned on a single rich-resource language pair, be it English-centered or not, our model is able to match the performance of the ones finetuned on all language pairs under the same data budget with less than 2. 0 points decrease in accuracy.

Machine Translation Retrieval +3

Near-Negative Distinction: Giving a Second Life to Human Evaluation Datasets

1 code implementation13 May 2022 Philippe Laban, Chien-Sheng Wu, Wenhao Liu, Caiming Xiong

Precisely assessing the progress in natural language generation (NLG) tasks is challenging, and human evaluation to establish a preference in a model's output over another is often necessary.

nlg evaluation Question Answering +3

Use All The Labels: A Hierarchical Multi-Label Contrastive Learning Framework

1 code implementation CVPR 2022 Shu Zhang, ran Xu, Caiming Xiong, Chetan Ramaiah

Current contrastive learning frameworks focus on leveraging a single supervisory signal to learn representations, which limits the efficacy on unseen data and downstream tasks.

All Contrastive Learning +1

A Generative Language Model for Few-shot Aspect-Based Sentiment Analysis

1 code implementation Findings (NAACL) 2022 Ehsan Hosseini-Asl, Wenhao Liu, Caiming Xiong

Our evaluation results on the single-task polarity prediction show that our approach outperforms the previous state-of-the-art (based on BERT) on average performance by a large margins in few-shot and full-shot settings.

Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA) +5

ELECRec: Training Sequential Recommenders as Discriminators

1 code implementation5 Apr 2022 Yongjun Chen, Jia Li, Caiming Xiong

A generator, as an auxiliary model, is trained jointly with the discriminator to sample plausible alternative next items and will be thrown out after training.

Sequential Recommendation

CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis

8 code implementations25 Mar 2022 Erik Nijkamp, Bo Pang, Hiroaki Hayashi, Lifu Tu, Huan Wang, Yingbo Zhou, Silvio Savarese, Caiming Xiong

To democratize this, we train and release a family of large language models up to 16. 1B parameters, called CODEGEN, on natural language and programming language data, and open source the training library JAXFORMER.

Code Generation HumanEval +4

Improving Contrastive Learning with Model Augmentation

1 code implementation25 Mar 2022 Zhiwei Liu, Yongjun Chen, Jia Li, Man Luo, Philip S. Yu, Caiming Xiong

However, existing methods all construct views by adopting augmentation from data perspectives, while we argue that 1) optimal data augmentation methods are hard to devise, 2) data augmentation methods destroy sequential correlations, and 3) data augmentation fails to incorporate comprehensive self-supervised signals.

Contrastive Learning Data Augmentation +3

ConTinTin: Continual Learning from Task Instructions

no code implementations ACL 2022 Wenpeng Yin, Jia Li, Caiming Xiong

This work defines a new learning paradigm ConTinTin (Continual Learning from Task Instructions), in which a system should learn a sequence of new tasks one by one, each task is explained by a piece of textual instruction.

Continual Learning

Long Document Summarization with Top-down and Bottom-up Inference

1 code implementation15 Mar 2022 Bo Pang, Erik Nijkamp, Wojciech Kryściński, Silvio Savarese, Yingbo Zhou, Caiming Xiong

Critical to the success of a summarization model is the faithful inference of latent representations of words or tokens in the source documents.

Structure Extraction in Task-Oriented Dialogues with Slot Clustering

2 code implementations28 Feb 2022 Liang Qiu, Chien-Sheng Wu, Wenhao Liu, Caiming Xiong

Extracting structure information from dialogue data can help us better understand user and system behaviors.

Clustering Data Augmentation +1

Efficient and Differentiable Conformal Prediction with General Function Classes

1 code implementation ICLR 2022 Yu Bai, Song Mei, Huan Wang, Yingbo Zhou, Caiming Xiong

Experiments show that our algorithm is able to learn valid prediction sets and improve the efficiency significantly over existing approaches in several applications such as prediction intervals with improved length, minimum-volume prediction sets for multi-output regression, and label prediction sets for image classification.

Conformal Prediction Image Classification +3

Intent Contrastive Learning for Sequential Recommendation

1 code implementation5 Feb 2022 Yongjun Chen, Zhiwei Liu, Jia Li, Julian McAuley, Caiming Xiong

Specifically, we introduce a latent variable to represent users' intents and learn the distribution function of the latent variable via clustering.

Contrastive Learning Model Optimization +3

BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation

9 code implementations28 Jan 2022 Junnan Li, Dongxu Li, Caiming Xiong, Steven Hoi

Furthermore, performance improvement has been largely achieved by scaling up the dataset with noisy image-text pairs collected from the web, which is a suboptimal source of supervision.

Ranked #3 on Open Vocabulary Attribute Detection on OVAD-Box benchmark (using extra training data)

Image Captioning Image-text matching +5

RGRecSys: A Toolkit for Robustness Evaluation of Recommender Systems

1 code implementation12 Jan 2022 Zohreh Ovaisi, Shelby Heinecke, Jia Li, Yongfeng Zhang, Elena Zheleva, Caiming Xiong

Robust machine learning is an increasingly important topic that focuses on developing models resilient to various forms of imperfect data.

Recommendation Systems

Value Retrieval with Arbitrary Queries for Form-like Documents

1 code implementation15 Dec 2021 Mingfei Gao, Le Xue, Chetan Ramaiah, Chen Xing, ran Xu, Caiming Xiong

Unlike previous methods that only address a fixed set of field items, our method predicts target value for an arbitrary query based on the understanding of the layout and semantics of a form.

document understanding Form +3

Open Vocabulary Object Detection with Pseudo Bounding-Box Labels

1 code implementation18 Nov 2021 Mingfei Gao, Chen Xing, Juan Carlos Niebles, Junnan Li, ran Xu, Wenhao Liu, Caiming Xiong

To enlarge the set of base classes, we propose a method to automatically generate pseudo bounding-box annotations of diverse objects from large-scale image-caption pairs.

Object object-detection +2

Dense Hierarchical Retrieval for Open-Domain Question Answering

1 code implementation Findings (EMNLP) 2021 Ye Liu, Kazuma Hashimoto, Yingbo Zhou, Semih Yavuz, Caiming Xiong, Philip S. Yu

In this work, we propose Dense Hierarchical Retrieval (DHR), a hierarchical framework that can generate accurate dense representations of passages by utilizing both macroscopic semantics in the document and microscopic semantics specific to each passage.

Open-Domain Question Answering Text Retrieval

Ensemble of Averages: Improving Model Selection and Boosting Performance in Domain Generalization

1 code implementation21 Oct 2021 Devansh Arpit, Huan Wang, Yingbo Zhou, Caiming Xiong

We first show that this chaotic behavior exists even along the training optimization trajectory of a single model, and propose a simple model averaging protocol that both significantly boosts domain generalization and diminishes the impact of stochasticity by improving the rank correlation between the in-domain validation accuracy and out-domain test accuracy, which is crucial for reliable early stopping.

Domain Generalization Model Selection

Learning Rich Nearest Neighbor Representations from Self-supervised Ensembles

no code implementations19 Oct 2021 Bram Wallace, Devansh Arpit, Huan Wang, Caiming Xiong

Pretraining convolutional neural networks via self-supervision, and applying them in transfer learning, is an incredibly fast-growing field that is rapidly and iteratively improving performance across practically all image domains.

Transfer Learning

Momentum Contrastive Autoencoder: Using Contrastive Learning for Latent Space Distribution Matching in WAE

no code implementations19 Oct 2021 Devansh Arpit, Aadyot Bhatnagar, Huan Wang, Caiming Xiong

Wasserstein autoencoder (WAE) shows that matching two distributions is equivalent to minimizing a simple autoencoder (AE) loss under the constraint that the latent space of this AE matches a pre-specified prior distribution.

Contrastive Learning Representation Learning

Improving Tail-Class Representation with Centroid Contrastive Learning

no code implementations19 Oct 2021 Anthony Meng Huat Tiong, Junnan Li, Guosheng Lin, Boyang Li, Caiming Xiong, Steven C. H. Hoi

ICCL interpolates two images from a class-agnostic sampler and a class-aware sampler, and trains the model such that the representation of the interpolative image can be used to retrieve the centroids for both source classes.

Contrastive Learning Image Classification +2

Improving Gender Fairness of Pre-Trained Language Models without Catastrophic Forgetting

no code implementations11 Oct 2021 Zahra Fatemi, Chen Xing, Wenhao Liu, Caiming Xiong

In this work, we empirically show that catastrophic forgetting occurs in such methods by evaluating them with general NLP tasks in GLUE.

coreference-resolution Fairness

Robustness Evaluation of Transformer-based Form Field Extractors via Form Attacks

1 code implementation8 Oct 2021 Le Xue, Mingfei Gao, Zeyuan Chen, Caiming Xiong, ran Xu

We propose a novel framework to evaluate the robustness of transformer-based form field extraction methods via form attacks.

Form Optical Character Recognition (OCR)

Self-supervised Learning for Sequential Recommendation with Model Augmentation

no code implementations29 Sep 2021 Zhiwei Liu, Yongjun Chen, Jia Li, Man Luo, Philip S. Yu, Caiming Xiong

However, existing methods all construct views by adopting augmentation from data perspectives, while we argue that 1) optimal data augmentation methods are hard to devise, 2) data augmentation methods destroy sequential correlations, and 3) data augmentation fails to incorporate comprehensive self-supervised signals.

Contrastive Learning Data Augmentation +2

Long Document Summarization with Top-Down and Bottom-Up Representation Inference

no code implementations29 Sep 2021 Bo Pang, Erik Nijkamp, Wojciech Maciej Kryscinski, Silvio Savarese, Yingbo Zhou, Caiming Xiong

Critical to the success of a summarization model is the faithful inference of latent representations of words or tokens in the source documents.

Document Summarization

Modeling Dynamic Attributes for Next Basket Recommendation

no code implementations23 Sep 2021 Yongjun Chen, Jia Li, Chenghao Liu, Chenxi Li, Markus Anderle, Julian McAuley, Caiming Xiong

However, properly integrating them into user interest models is challenging since attribute dynamics can be diverse such as time-interval aware, periodic patterns (etc.

Attribute Next-basket recommendation

RnG-KBQA: Generation Augmented Iterative Ranking for Knowledge Base Question Answering

1 code implementation ACL 2022 Xi Ye, Semih Yavuz, Kazuma Hashimoto, Yingbo Zhou, Caiming Xiong

We present RnG-KBQA, a Rank-and-Generate approach for KBQA, which remedies the coverage issue with a generation model while preserving a strong generalization capability.

Entity Linking Knowledge Base Question Answering +1

Contrastive Self-supervised Sequential Recommendation with Robust Augmentation

1 code implementation14 Aug 2021 Zhiwei Liu, Yongjun Chen, Jia Li, Philip S. Yu, Julian McAuley, Caiming Xiong

In this paper, we investigate the application of contrastive Self-Supervised Learning (SSL) to the sequential recommendation, as a way to alleviate some of these issues.

Contrastive Learning Self-Supervised Learning +1

A Theory-Driven Self-Labeling Refinement Method for Contrastive Representation Learning

no code implementations NeurIPS 2021 Pan Zhou, Caiming Xiong, Xiao-Tong Yuan, Steven Hoi

Although intuitive, such a native label assignment strategy cannot reveal the underlying semantic similarity between a query and its positives and negatives, and impairs performance, since some negatives are semantically similar to the query or even share the same semantic class as the query.

Contrastive Learning Representation Learning +2

Understanding the Under-Coverage Bias in Uncertainty Estimation

no code implementations NeurIPS 2021 Yu Bai, Song Mei, Huan Wang, Caiming Xiong

Estimating the data uncertainty in regression tasks is often done by learning a quantile function or a prediction interval of the true label conditioned on the input.

parameter estimation quantile regression

Policy Finetuning: Bridging Sample-Efficient Offline and Online Reinforcement Learning

no code implementations NeurIPS 2021 Tengyang Xie, Nan Jiang, Huan Wang, Caiming Xiong, Yu Bai

This offline result is the first that matches the sample complexity lower bound in this setting, and resolves a recent open question in offline RL.

Offline RL Open-Ended Question Answering +3

Evaluating State-of-the-Art Classification Models Against Bayes Optimality

1 code implementation NeurIPS 2021 Ryan Theisen, Huan Wang, Lav R. Varshney, Caiming Xiong, Richard Socher

Moreover, we show that by varying the temperature of the learned flow models, we can generate synthetic datasets that closely resemble standard benchmark datasets, but with almost any desired Bayes error.

Unsupervised Out-of-Domain Detection via Pre-trained Transformers

1 code implementation ACL 2021 Keyang Xu, Tongzheng Ren, Shikun Zhang, Yihao Feng, Caiming Xiong

Deployed real-world machine learning applications are often subject to uncontrolled and even potentially malicious inputs.

Cannot find the paper you are looking for? You can Submit a new open access paper.