no code implementations • EMNLP 2021 • Jiaxin Huang, Chunyuan Li, Krishan Subudhi, Damien Jose, Shobana Balakrishnan, Weizhu Chen, Baolin Peng, Jianfeng Gao, Jiawei Han
This paper presents an empirical study to efficiently build named entity recognition (NER) systems when a small amount of in-domain labeled data is available.
1 code implementation • EMNLP 2021 • Yuji Zhang, Yubo Zhang, Chunpu Xu, Jing Li, Ziyan Jiang, Baolin Peng
It is hypothesized that one’s interests in a hashtag are related with what they said before (user history) and the existing posts present the hashtag (hashtag contexts).
no code implementations • 15 Oct 2024 • Seonghyeon Ye, Joel Jang, Byeongguk Jeon, Sejune Joo, Jianwei Yang, Baolin Peng, Ajay Mandlekar, Reuben Tan, Yu-Wei Chao, Bill Yuchen Lin, Lars Liden, Kimin Lee, Jianfeng Gao, Luke Zettlemoyer, Dieter Fox, Minjoon Seo
We introduce Latent Action Pretraining for general Action models (LAPA), an unsupervised method for pretraining Vision-Language-Action (VLA) models without ground-truth robot action labels.
no code implementations • 9 Oct 2024 • Xiyao Wang, Linfeng Song, Ye Tian, Dian Yu, Baolin Peng, Haitao Mi, Furong Huang, Dong Yu
Monte Carlo Tree Search (MCTS) has recently emerged as a powerful technique for enhancing the reasoning capabilities of LLMs.
no code implementations • 2 Oct 2024 • Xiao Yu, Baolin Peng, Vineeth Vajipey, Hao Cheng, Michel Galley, Jianfeng Gao, Zhou Yu
Autonomous agents have demonstrated significant potential in automating complex multistep decision-making tasks.
no code implementations • 28 Aug 2024 • Dian Yu, Baolin Peng, Ye Tian, Linfeng Song, Haitao Mi, Dong Yu
There is a growing trend of teaching large language models (LLMs) to solve mathematical problems through coding.
no code implementations • 30 Jun 2024 • Yuheng Zhang, Dian Yu, Baolin Peng, Linfeng Song, Ye Tian, Mingyue Huo, Nan Jiang, Haitao Mi, Dong Yu
Specifically, we formulate the problem as a two-player game and propose a novel online algorithm, iterative Nash policy optimization (INPO).
no code implementations • 29 Jun 2024 • Ante Wang, Linfeng Song, Ye Tian, Baolin Peng, Dian Yu, Haitao Mi, Jinsong Su, Dong Yu
Recent research suggests that tree search algorithms (e. g. Monte Carlo Tree Search) can dramatically boost LLM performance on complex mathematical reasoning tasks.
no code implementations • 10 Jun 2024 • Xiaoying Zhang, Baolin Peng, Ye Tian, Jingyan Zhou, YiPeng Zhang, Haitao Mi, Helen Meng
Motivated by the remarkable success of the Feynman Technique in efficient human learning, we introduce Self-Tuning, a learning framework aimed at improving an LLM's ability to effectively acquire new knowledge from raw documents through self-teaching.
1 code implementation • 18 Apr 2024 • Ye Tian, Baolin Peng, Linfeng Song, Lifeng Jin, Dian Yu, Haitao Mi, Dong Yu
Despite the impressive capabilities of Large Language Models (LLMs) on various tasks, they still struggle with scenarios that involves complex reasoning and planning.
Ranked #1 on
GSM8K
on GSM8K
(Accuracy metric)
no code implementations • 14 Apr 2024 • Souvik Das, Lifeng Jin, Linfeng Song, Haitao Mi, Baolin Peng, Dong Yu
Current state-of-the-art approaches refine decoding by contrasting early-exit distributions from a lower layer with the final layer to exploit information related to factuality within the model forward procedure.
no code implementations • 30 Mar 2024 • Ben Zhou, Hongming Zhang, Sihao Chen, Dian Yu, Hongwei Wang, Baolin Peng, Dan Roth, Dong Yu
Conceptual reasoning, the ability to reason in abstract and high-level perspectives, is key to generalization in human cognition.
no code implementations • 14 Mar 2024 • Ante Wang, Linfeng Song, Ye Tian, Baolin Peng, Lifeng Jin, Haitao Mi, Jinsong Su, Dong Yu
Calibration, which establishes the correlation between accuracy and model confidence, is important for LLM development.
no code implementations • 28 Feb 2024 • Lifeng Jin, Baolin Peng, Linfeng Song, Haitao Mi, Ye Tian, Dong Yu
The most common training pipeline for large language models includes pretraining, finetuning and aligning phases, with their respective resulting models, such as the pretrained model and the finetuned model.
no code implementations • 23 Feb 2024 • Ante Wang, Linfeng Song, Baolin Peng, Ye Tian, Lifeng Jin, Haitao Mi, Jinsong Su, Dong Yu
Experiments on Biographies show that our method can effectively improve the factuality of generations with simple and intuitive prompts across different scales of LLMs.
no code implementations • 14 Feb 2024 • Xiaoying Zhang, Baolin Peng, Ye Tian, Jingyan Zhou, Lifeng Jin, Linfeng Song, Haitao Mi, Helen Meng
Despite showing increasingly human-like abilities, large language models (LLMs) often struggle with factual inaccuracies, i. e. "hallucinations", even when they hold relevant knowledge.
1 code implementation • 7 Nov 2023 • Sihao Chen, Hongming Zhang, Tong Chen, Ben Zhou, Wenhao Yu, Dian Yu, Baolin Peng, Hongwei Wang, Dan Roth, Dong Yu
We introduce sub-sentence encoder, a contrastively-learned contextual embedding model for fine-grained semantic representation of text.
1 code implementation • 20 Oct 2023 • Xiao Yu, Baolin Peng, Michel Galley, Jianfeng Gao, Zhou Yu
The self-improving ability of large language models (LLMs), enabled by prompting them to analyze and revise their own outputs, has garnered significant interest in recent research.
1 code implementation • 28 Sep 2023 • Lingfeng Shen, Sihao Chen, Linfeng Song, Lifeng Jin, Baolin Peng, Haitao Mi, Daniel Khashabi, Dong Yu
We propose Contrast Instructions -- a benchmarking strategy for the consistency of RM.
no code implementations • 18 Sep 2023 • Baolin Peng, Linfeng Song, Ye Tian, Lifeng Jin, Haitao Mi, Dong Yu
Large Language Models (LLMs) have revolutionized natural language processing, yet aligning these models with human values and preferences using RLHF remains a significant challenge.
2 code implementations • 17 Aug 2023 • Zekun Li, Baolin Peng, Pengcheng He, Xifeng Yan
In this work, we establish a benchmark to evaluate the robustness of instruction-following LLMs against prompt injection attacks.
1 code implementation • 24 May 2023 • Miaoran Li, Baolin Peng, Michel Galley, Jianfeng Gao, Zhu Zhang
Fact-checking is an essential task in NLP that is commonly utilized for validating the factual accuracy of claims.
no code implementations • 15 May 2023 • Xiaoying Zhang, Baolin Peng, Kun Li, Jingyan Zhou, Helen Meng
Building end-to-end task bots and maintaining their integration with new functionalities using minimal human efforts is a long-standing challenge in dialog research.
no code implementations • 1 May 2023 • Qiuyuan Huang, Jae Sung Park, Abhinav Gupta, Paul Bennett, Ran Gong, Subhojit Som, Baolin Peng, Owais Khan Mohammed, Chris Pal, Yejin Choi, Jianfeng Gao
In this study, we develop an infinite agent that learns to transfer knowledge memory from general foundation models (e. g. GPT4, DALLE) to novel domains or scenarios for scene understanding and generation in the physical or virtual world.
1 code implementation • NeurIPS 2023 • Pan Lu, Baolin Peng, Hao Cheng, Michel Galley, Kai-Wei Chang, Ying Nian Wu, Song-Chun Zhu, Jianfeng Gao
At the heart of Chameleon is an LLM-based planner that assembles a sequence of tools to execute to generate the final response.
2 code implementations • 6 Apr 2023 • Baolin Peng, Chunyuan Li, Pengcheng He, Michel Galley, Jianfeng Gao
Prior work has shown that finetuning large language models (LLMs) using machine-generated instruction-following data enables such models to achieve remarkable zero-shot capabilities on new tasks, and no human-written instructions are needed.
no code implementations • 2 Mar 2023 • Felix Faltings, Michel Galley, Baolin Peng, Kianté Brantley, Weixin Cai, Yizhe Zhang, Jianfeng Gao, Bill Dolan
Unfortunately, this means most of the research on text, code, and image generation has focused on non-interactive settings, whereby the model is expected to get everything right without accounting for any input from a user who may be willing to help.
no code implementations • 24 Feb 2023 • Baolin Peng, Michel Galley, Pengcheng He, Hao Cheng, Yujia Xie, Yu Hu, Qiuyuan Huang, Lars Liden, Zhou Yu, Weizhu Chen, Jianfeng Gao
Large language models (LLMs), such as ChatGPT, are able to generate human-like, fluent responses for many downstream tasks, e. g., task-oriented dialog and question answering.
1 code implementation • NeurIPS 2023 • Zekun Li, Baolin Peng, Pengcheng He, Michel Galley, Jianfeng Gao, Xifeng Yan
Our experiments demonstrate that the framework consistently improves LLMs' (e. g., ChatGPT, Codex, InstructGPT) performance on these supervised tasks using minimal labeled data.
no code implementations • 20 Dec 2022 • Yu Li, Baolin Peng, Pengcheng He, Michel Galley, Zhou Yu, Jianfeng Gao
In this work, we propose DIONYSUS (dynamic input optimization in pre-training for dialogue summarization), a pre-trained encoder-decoder model for summarizing dialogues in any new domain.
no code implementations • 20 Dec 2022 • Miaoran Li, Baolin Peng, Michel Galley, Jianfeng Gao, Zhu Zhang
To better mimic human-level conversations that usually fuse various dialog modes, it is essential to build a system that can effectively handle both TOD and ODD and access different knowledge sources.
no code implementations • 4 Dec 2022 • Faeze Brahman, Baolin Peng, Michel Galley, Sudha Rao, Bill Dolan, Snigdha Chaturvedi, Jianfeng Gao
We propose a new grounded keys-to-text generation task: the task is to generate a factual description about an entity given a set of guiding keys, and grounding passages.
1 code implementation • 30 Nov 2022 • Qi Zhu, Christian Geishauser, Hsien-Chin Lin, Carel van Niekerk, Baolin Peng, Zheng Zhang, Michael Heck, Nurul Lubis, Dazhen Wan, Xiaochen Zhu, Jianfeng Gao, Milica Gašić, Minlie Huang
Task-oriented dialogue (TOD) systems function as digital assistants, guiding users through various tasks such as booking flights or finding restaurants.
no code implementations • 13 Oct 2022 • Shiyang Li, Jianshu Chen, Yelong Shen, Zhiyu Chen, Xinlu Zhang, Zekun Li, Hong Wang, Jing Qian, Baolin Peng, Yi Mao, Wenhu Chen, Xifeng Yan
Integrating free-text explanations to in-context learning of large language models (LLM) is shown to elicit strong reasoning capabilities along with reasonable explanations.
1 code implementation • 21 Aug 2022 • Pengcheng He, Baolin Peng, Liyang Lu, Song Wang, Jie Mei, Yang Liu, Ruochen Xu, Hany Hassan Awadalla, Yu Shi, Chenguang Zhu, Wayne Xiong, Michael Zeng, Jianfeng Gao, Xuedong Huang
Z-Code++ creates new state of the art on 9 out of 13 text summarization tasks across 5 languages.
1 code implementation • 24 Jun 2022 • Miaoran Li, Baolin Peng, Jianfeng Gao, Zhu Zhang
Existing studies in conversational AI mostly treat task-oriented dialog (TOD) and question answering (QA) as separate tasks.
1 code implementation • 22 Jun 2022 • Baolin Peng, Michel Galley, Pengcheng He, Chris Brockett, Lars Liden, Elnaz Nouri, Zhou Yu, Bill Dolan, Jianfeng Gao
We introduce GODEL (Grounded Open Dialogue Language Model), a large pre-trained language model for dialog.
no code implementations • SIGDIAL (ACL) 2022 • Xiaoying Zhang, Baolin Peng, Jianfeng Gao, Helen Meng
In this paper, we study the problem of automatically adapting task bots to changing environments by learning from human-bot interactions with minimum or zero human annotations.
no code implementations • NAACL 2022 • Yu Li, Baolin Peng, Yelong Shen, Yi Mao, Lars Liden, Zhou Yu, Jianfeng Gao
To address these challenges, we present PLUG, a language model that homogenizes different knowledge sources to a unified knowledge representation for knowledge-grounded dialogue generation tasks.
no code implementations • 12 Dec 2021 • Liang Qiu, Yizhou Zhao, Jinchao Li, Pan Lu, Baolin Peng, Jianfeng Gao, Song-Chun Zhu
To the best of our knowledge, ValueNet is the first large-scale text dataset for human value modeling, and we are the first one trying to incorporate a value model into emotionally intelligent dialogue systems.
no code implementations • 21 Oct 2021 • Baolin Peng, Chunyuan Li, Zhu Zhang, Jinchao Li, Chenguang Zhu, Jianfeng Gao
We propose SYNERGY, a hybrid learning framework where a task bot is developed in two steps: (i) Symbolic knowledge to neural networks: Large amounts of simulated dialog sessions are generated based on task-specific symbolic knowledge which is represented as a task schema consisting of dialog flows and task-oriented databases.
1 code implementation • ACL 2021 • Zexin Lu, Keyang Ding, Yuji Zhang, Jing Li, Baolin Peng, Lemao Liu
This paper presents a novel task to generate poll questions for social media posts.
Ranked #3 on
Answer Generation
on WeiboPolls
no code implementations • ACL 2021 • Liang Qiu, Yuan Liang, Yizhou Zhao, Pan Lu, Baolin Peng, Zhou Yu, Ying Nian Wu, Song-Chun Zhu
Inferring social relations from dialogues is vital for building emotionally intelligent robots to interpret human language better and act accordingly.
Ranked #5 on
Dialog Relation Extraction
on DialogRE
no code implementations • ACL 2021 • Baolin Peng, Chunyuan Li, Zhu Zhang, Chenguang Zhu, Jinchao Li, Jianfeng Gao
For task-oriented dialog systems to be maximally useful, it must be able to process conversations in a way that is (1) generalizable with a small number of training examples for new task domains, and (2) robust to user input in various styles, modalities or domains.
2 code implementations • 29 Dec 2020 • Jiaxin Huang, Chunyuan Li, Krishan Subudhi, Damien Jose, Shobana Balakrishnan, Weizhu Chen, Baolin Peng, Jianfeng Gao, Jiawei Han
This paper presents a comprehensive study to efficiently build named entity recognition (NER) systems when a small number of in-domain labeled data is available.
no code implementations • 25 Dec 2020 • Chunyuan Li, Xiujun Li, Lei Zhang, Baolin Peng, Mingyuan Zhou, Jianfeng Gao
Self-supervised pre-training (SSP) employs random image transformations to generate training data for visual representation learning.
Ranked #71 on
Self-Supervised Image Classification
on ImageNet
no code implementations • 12 Nov 2020 • Chulaka Gunasekara, Seokhwan Kim, Luis Fernando D'Haro, Abhinav Rastogi, Yun-Nung Chen, Mihail Eric, Behnam Hedayatnia, Karthik Gopalakrishnan, Yang Liu, Chao-Wei Huang, Dilek Hakkani-Tür, Jinchao Li, Qi Zhu, Lingxiao Luo, Lars Liden, Kaili Huang, Shahin Shayandeh, Runze Liang, Baolin Peng, Zheng Zhang, Swadheen Shukla, Minlie Huang, Jianfeng Gao, Shikib Mehri, Yulan Feng, Carla Gordon, Seyed Hossein Alavi, David Traum, Maxine Eskenazi, Ahmad Beirami, Eunjoon, Cho, Paul A. Crook, Ankita De, Alborz Geramifard, Satwik Kottur, Seungwhan Moon, Shivani Poddar, Rajen Subba
Interactive evaluation of dialog, and 4.
1 code implementation • Findings of the Association for Computational Linguistics 2020 • Ziming Li, Sungjin Lee, Baolin Peng, Jinchao Li, Julia Kiseleva, Maarten de Rijke, Shahin Shayandeh, Jianfeng Gao
Reinforcement learning methods have emerged as a popular choice for training an efficient and effective dialogue policy.
no code implementations • 7 Sep 2020 • Jianfeng Gao, Baolin Peng, Chunyuan Li, Jinchao Li, Shahin Shayandeh, Lars Liden, Heung-Yeung Shum
This article provides an overview of this progress and discusses related methods and technologies that can be incorporated for building robust conversational AI systems.
no code implementations • ACL 2020 • Huimin Wang, Baolin Peng, Kam-Fai Wong
Training a task-oriented dialogue agent with reinforcement learning is prohibitively expensive since it requires a large volume of interactions with users.
no code implementations • ACL 2020 • Swadheen Shukla, Lars Liden, Shay, Shahin eh, Eslam Kamal, Jinchao Li, Matt Mazzola, Thomas Park, Baolin Peng, Jianfeng Gao
Traditionally, industry solutions for building a task-oriented dialog system have relied on helping dialog authors define rule-based dialog managers, represented as dialog flows.
no code implementations • 3 Jun 2020 • Yumo Xu, Chenguang Zhu, Baolin Peng, Michael Zeng
Dialog policy determines the next-step actions for agents and hence is central to a dialogue system.
no code implementations • SIGDIAL (ACL) 2020 • Ryuichi Takanobu, Qi Zhu, Jinchao Li, Baolin Peng, Jianfeng Gao, Minlie Huang
There is a growing interest in developing goal-oriented dialog systems which serve users in accomplishing complex tasks through multi-turn conversations.
1 code implementation • 11 May 2020 • Baolin Peng, Chunyuan Li, Jinchao Li, Shahin Shayandeh, Lars Liden, Jianfeng Gao
We present a new method SOLOIST that uses transfer learning and machine teaching to build task bots at scale.
Ranked #4 on
End-To-End Dialogue Modelling
on MULTIWOZ 2.0
4 code implementations • 29 Apr 2020 • Cheng Zhong, Kangenbei Liao, Wei Chen, Qianlong Liu, Baolin Peng, Xuanjing Huang, Jiajie Peng, Zhongyu Wei
Existing approaches usually employ a flat policy structure that treat all symptoms and diseases equally for action making.
Hierarchical Reinforcement Learning
reinforcement-learning
+2
1 code implementation • 29 Apr 2020 • Baolin Peng, Chenguang Zhu, Michael Zeng, Jianfeng Gao
The training of spoken language understanding (SLU) models often faces the problem of data scarcity.
no code implementations • 9 Apr 2020 • Swadheen Shukla, Lars Liden, Shahin Shayandeh, Eslam Kamal, Jinchao Li, Matt Mazzola, Thomas Park, Baolin Peng, Jianfeng Gao
Traditionally, industry solutions for building a task-oriented dialog system have relied on helping dialog authors define rule-based dialog managers, represented as dialog flows.
1 code implementation • 7 Apr 2020 • Ziming Li, Sungjin Lee, Baolin Peng, Jinchao Li, Julia Kiseleva, Maarten de Rijke, Shahin Shayandeh, Jianfeng Gao
Reinforcement Learning (RL) methods have emerged as a popular choice for training an efficient and effective dialogue policy.
1 code implementation • EMNLP 2020 • Chunyuan Li, Xiang Gao, Yuan Li, Baolin Peng, Xiujun Li, Yizhe Zhang, Jianfeng Gao
We hope that our first pre-trained big VAE language model itself and results can help the NLP community renew the interests of deep generative models in the era of large-scale pre-training, and make these principled methods more practical.
2 code implementations • Findings of the Association for Computational Linguistics 2020 • Baolin Peng, Chenguang Zhu, Chunyuan Li, Xiujun Li, Jinchao Li, Michael Zeng, Jianfeng Gao
It is pre-trained on a large set of annotated NLG corpus to acquire the controllable generation ability, and fine-tuned with only a few domain-specific labels to adapt to new domains.
Ranked #4 on
Data-to-Text Generation
on MULTIWOZ 2.1
1 code implementation • ACL 2020 • Qi Zhu, Zheng Zhang, Yan Fang, Xiang Li, Ryuichi Takanobu, Jinchao Li, Baolin Peng, Jianfeng Gao, Xiaoyan Zhu, Minlie Huang
We present ConvLab-2, an open-source toolkit that enables researchers to build task-oriented dialogue systems with state-of-the-art models, perform an end-to-end evaluation, and diagnose the weakness of systems.
no code implementations • 14 Nov 2019 • Seokhwan Kim, Michel Galley, Chulaka Gunasekara, Sungjin Lee, Adam Atkinson, Baolin Peng, Hannes Schulz, Jianfeng Gao, Jinchao Li, Mahmoud Adada, Minlie Huang, Luis Lastras, Jonathan K. Kummerfeld, Walter S. Lasecki, Chiori Hori, Anoop Cherian, Tim K. Marks, Abhinav Rastogi, Xiaoxue Zang, Srinivas Sunkara, Raghav Gupta
This paper introduces the Eighth Dialog System Technology Challenge.
2 code implementations • ACL 2019 • Sungjin Lee, Qi Zhu, Ryuichi Takanobu, Xiang Li, Yaoqin Zhang, Zheng Zhang, Jinchao Li, Baolin Peng, Xiujun Li, Minlie Huang, Jianfeng Gao
We present ConvLab, an open-source multi-domain end-to-end dialog system platform, that enables researchers to quickly set up experiments with reusable components and compare a large set of different approaches, ranging from conventional pipeline systems to end-to-end neural models, in common environments.
no code implementations • ACL 2018 • Zhongyu Wei, Qianlong Liu, Baolin Peng, Huaixiao Tou, Ting Chen, Xuanjing Huang, Kam-Fai Wong, Xiangying Dai
In this paper, we make a move to build a dialogue system for automatic diagnosis.
3 code implementations • ACL 2018 • Baolin Peng, Xiujun Li, Jianfeng Gao, Jingjing Liu, Kam-Fai Wong, Shang-Yu Su
During dialogue policy learning, the world model is constantly updated with real user experience to approach real user behavior, and in turn, the dialogue agent is optimized using both real experience and simulated experience.
no code implementations • 31 Oct 2017 • Baolin Peng, Xiujun Li, Jianfeng Gao, Jingjing Liu, Yun-Nung Chen, Kam-Fai Wong
This paper presents a new method --- adversarial advantage actor-critic (Adversarial A2C), which significantly improves the efficiency of dialogue policy learning in task-completion dialogue systems.
no code implementations • EMNLP 2017 • Baolin Peng, Xiujun Li, Lihong Li, Jianfeng Gao, Asli Celikyilmaz, Sungjin Lee, Kam-Fai Wong
Building a dialogue agent to fulfill complex tasks, such as travel planning, is challenging because the agent has to learn to collectively complete multiple subtasks.
no code implementations • EACL 2017 • Baolin Peng, Michael Seltzer, Y.C. Ju, Geoffrey Zweig, Kam-Fai Wong
This is motivated by an actual system under development to assist in the order taking process.
no code implementations • COLING 2016 • Shichao Dong, Gabriel Pui Cheong Fung, Binyang Li, Baolin Peng, Ming Liao, Jia Zhu, Kam-Fai Wong
We present a system called ACE for Automatic Colloquialism and Errors detection for written Chinese.
no code implementations • 3 Jun 2016 • Kaisheng Yao, Baolin Peng, Geoffrey Zweig, Kam-Fai Wong
Experimental results indicate that the model outperforms previously proposed neural conversation architectures, and that using specificity in the objective function significantly improves performances for both generation and retrieval.
no code implementations • 15 Nov 2015 • Yikang Shen, Wenge Rong, Nan Jiang, Baolin Peng, Jie Tang, Zhang Xiong
With the development of community based question answering (Q&A) services, a large scale of Q&A archives have been accumulated and are an important information and knowledge resource on the web.
no code implementations • 29 Oct 2015 • Kaisheng Yao, Geoffrey Zweig, Baolin Peng
The intention network is a recurrent network that models the dynamics of the intention process.
1 code implementation • 22 Aug 2015 • Baolin Peng, Zhengdong Lu, Hang Li, Kam-Fai Wong
For example, it improves the accuracy on Path Finding(10K) from 33. 4% [6] to over 98%.
no code implementations • 31 May 2015 • Baolin Peng, Kaisheng Yao
Recurrent Neural Networks (RNNs) have become increasingly popular for the task of language understanding.