Search Results for author: Binyuan Hui

Found 29 papers, 18 papers with code

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.

An Investigation of LLMs' Inefficacy in Understanding Converse Relations

1 code implementation8 Oct 2023 Chengwen Qi, Bowen Li, Binyuan Hui, Bailin Wang, Jinyang Li, Jinwang Wu, Yuanjun Laili

Our ConvRE features two tasks, Re2Text and Text2Re, which are formulated as multi-choice question answering to evaluate LLMs' ability to determine the matching between relations and associated text.

Knowledge Graph Completion Question Answering +1

VDialogUE: A Unified Evaluation Benchmark for Visually-grounded Dialogue

no code implementations14 Sep 2023 Yunshui Li, Binyuan Hui, Zhaochao Yin, Wanwei He, Run Luo, Yuxing Long, Min Yang, Fei Huang, Yongbin Li

Visually-grounded dialog systems, which integrate multiple modes of communication such as text and visual inputs, have become an increasingly popular area of investigation.

Model Inversion Attack via Dynamic Memory Learning

no code implementations24 Aug 2023 Gege Qi, Yuefeng Chen, Xiaofeng Mao, Binyuan Hui, Xiaodan Li, Rong Zhang, Hui Xue

Model Inversion (MI) attacks aim to recover the private training data from the target model, which has raised security concerns about the deployment of DNNs in practice.

OctoPack: Instruction Tuning Code Large Language Models

2 code implementations14 Aug 2023 Niklas Muennighoff, Qian Liu, Armel Zebaze, Qinkai Zheng, Binyuan Hui, Terry Yue Zhuo, Swayam Singh, Xiangru Tang, Leandro von Werra, Shayne Longpre

We benchmark CommitPack against other natural and synthetic code instructions (xP3x, Self-Instruct, OASST) on the 16B parameter StarCoder model, and achieve state-of-the-art performance among models not trained on OpenAI outputs, on the HumanEval Python benchmark (46. 2% pass@1).

Code Generation Code Repair

A Preliminary Study of the Intrinsic Relationship between Complexity and Alignment

1 code implementation10 Aug 2023 Yingxiu Zhao, Bowen Yu, Binyuan Hui, Haiyang Yu, Fei Huang, Yongbin Li, Nevin L. Zhang

By adjusting the number of added nodes, we can control the difficulty level in the modified instruction data.

Multimodal Recommendation Dialog with Subjective Preference: A New Challenge and Benchmark

1 code implementation26 May 2023 Yuxing Long, Binyuan Hui, Caixia Yuan1, Fei Huang, Yongbin Li, Xiaojie Wang

Existing multimodal task-oriented dialog data fails to demonstrate the diverse expressions of user subjective preferences and recommendation acts in the real-life shopping scenario.

PaCE: Unified Multi-modal Dialogue Pre-training with Progressive and Compositional Experts

1 code implementation24 May 2023 Yunshui Li, Binyuan Hui, Zhichao Yin, Min Yang, Fei Huang, Yongbin Li

It utilizes a combination of several fundamental experts to accommodate multiple dialogue-related tasks and can be pre-trained using limited dialogue and extensive non-dialogue multi-modal data.

Dialogue State Tracking Image Retrieval +4

Iterative Forward Tuning Boosts In-context Learning in Language Models

no code implementations22 May 2023 Jiaxi Yang, Binyuan Hui, Min Yang, Binhua Li, Fei Huang, Yongbin Li

In this paper, we propose an effective and efficient two-stage framework to boost ICL in LLMs by exploiting a dual form between Transformer attention and gradient descent-based optimization.

Decision Making Multiple-choice

Out-of-Domain Intent Detection Considering Multi-turn Dialogue Contexts

no code implementations5 May 2023 Hao Lang, Yinhe Zheng, Binyuan Hui, Fei Huang, Yongbin Li

Out-of-Domain (OOD) intent detection is vital for practical dialogue systems, and it usually requires considering multi-turn dialogue contexts.

Intent Detection

Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs

1 code implementation4 May 2023 Jinyang Li, Binyuan Hui, Ge Qu, Jiaxi Yang, Binhua Li, Bowen Li, Bailin Wang, Bowen Qin, Rongyu Cao, Ruiying Geng, Nan Huo, Xuanhe Zhou, Chenhao Ma, Guoliang Li, Kevin C. C. Chang, Fei Huang, Reynold Cheng, Yongbin Li

Our emphasis on database values highlights the new challenges of dirty database contents, external knowledge between NL questions and database contents, and SQL efficiency, particularly in the context of massive databases.

Semantic Parsing SQL Parsing +1

Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for Table-based Reasoning

1 code implementation31 Jan 2023 Yunhu Ye, Binyuan Hui, Min Yang, Binhua Li, Fei Huang, Yongbin Li

To alleviate the above challenges, we exploit large language models (LLMs) as decomposers for effective table-based reasoning, which (i) decompose huge evidence (a huge table) into sub-evidence (a small table) to mitigate the interference of useless information for table reasoning; and (ii) decompose complex questions into simpler sub-questions for text reasoning.

Semantic Parsing Table-based Fact Verification

Graphix-T5: Mixing Pre-Trained Transformers with Graph-Aware Layers for Text-to-SQL Parsing

1 code implementation18 Jan 2023 Jinyang Li, Binyuan Hui, Reynold Cheng, Bowen Qin, Chenhao Ma, Nan Huo, Fei Huang, Wenyu Du, Luo Si, Yongbin Li

Recently, the pre-trained text-to-text transformer model, namely T5, though not specialized for text-to-SQL parsing, has achieved state-of-the-art performance on standard benchmarks targeting domain generalization.

Domain Generalization Inductive Bias +3

SPRING: Situated Conversation Agent Pretrained with Multimodal Questions from Incremental Layout Graph

1 code implementation5 Jan 2023 Yuxing Long, Binyuan Hui, Fulong Ye, Yanyang Li, Zhuoxin Han, Caixia Yuan, Yongbin Li, Xiaojie Wang

Existing multimodal conversation agents have shown impressive abilities to locate absolute positions or retrieve attributes in simple scenarios, but they fail to perform well when complex relative positions and information alignments are involved, which poses a bottleneck in response quality.

Question Answering

STAR: SQL Guided Pre-Training for Context-dependent Text-to-SQL Parsing

1 code implementation21 Oct 2022 ZeFeng Cai, Xiangyu Li, Binyuan Hui, Min Yang, Bowen Li, Binhua Li, Zheng Cao, Weijie Li, Fei Huang, Luo Si, Yongbin Li

Concretely, we propose two novel pre-training objectives which respectively explore the context-dependent interactions of NL utterances and SQL queries within each text-to-SQL conversation: (i) schema state tracking (SST) objective that tracks and explores the schema states of context-dependent SQL queries in the form of schema-states by predicting and updating the value of each schema slot during interaction; (ii) utterance dependency tracking (UDT) objective that employs weighted contrastive learning to pull together two semantically similar NL utterances and push away the representations of semantically dissimilar NL utterances within each conversation.

Contrastive Learning SQL Parsing +1

SUN: Exploring Intrinsic Uncertainties in Text-to-SQL Parsers

1 code implementation COLING 2022 Bowen Qin, Lihan Wang, Binyuan Hui, Bowen Li, Xiangpeng Wei, Binhua Li, Fei Huang, Luo Si, Min Yang, Yongbin Li

To improve the generalizability and stability of neural text-to-SQL parsers, we propose a model uncertainty constraint to refine the query representations by enforcing the output representations of different perturbed encoding networks to be consistent with each other.

SQL Parsing Text-To-SQL

A Survey on Text-to-SQL Parsing: Concepts, Methods, and Future Directions

no code implementations29 Aug 2022 Bowen Qin, Binyuan Hui, Lihan Wang, Min Yang, Jinyang Li, Binhua Li, Ruiying Geng, Rongyu Cao, Jian Sun, Luo Si, Fei Huang, Yongbin Li

In recent years, deep neural networks have significantly advanced this task by neural generation models, which automatically learn a mapping function from an input NL question to an output SQL query.

SQL Parsing Text-To-SQL

Proton: Probing Schema Linking Information from Pre-trained Language Models for Text-to-SQL Parsing

2 code implementations28 Jun 2022 Lihan Wang, Bowen Qin, Binyuan Hui, Bowen Li, Min Yang, Bailin Wang, Binhua Li, Fei Huang, Luo Si, Yongbin Li

The importance of building text-to-SQL parsers which can be applied to new databases has long been acknowledged, and a critical step to achieve this goal is schema linking, i. e., properly recognizing mentions of unseen columns or tables when generating SQLs.

SQL Parsing Text-To-SQL

S$^2$SQL: Injecting Syntax to Question-Schema Interaction Graph Encoder for Text-to-SQL Parsers

no code implementations14 Mar 2022 Binyuan Hui, Ruiying Geng, Lihan Wang, Bowen Qin, Bowen Li, Jian Sun, Yongbin Li

The task of converting a natural language question into an executable SQL query, known as text-to-SQL, is an important branch of semantic parsing.

Semantic Parsing Text-To-SQL

Linking-Enhanced Pre-Training for Table Semantic Parsing

no code implementations18 Nov 2021 Bowen Qin, Lihan Wang, Binyuan Hui, Ruiying Geng, Zheng Cao, Min Yang, Jian Sun, Yongbin Li

Recently pre-training models have significantly improved the performance of various NLP tasks by leveraging large-scale text corpora to improve the contextual representation ability of the neural network.

Inductive Bias Language Modelling +2

Improving Text-to-SQL with Schema Dependency Learning

no code implementations7 Mar 2021 Binyuan Hui, Xiang Shi, Ruiying Geng, Binhua Li, Yongbin Li, Jian Sun, Xiaodan Zhu

In this paper, we present the Schema Dependency guided multi-task Text-to-SQL model (SDSQL) to guide the network to effectively capture the interactions between questions and schemas.


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