语言大模型 / LLM - arXivDaily 专题

2402.00658 2024-10-16 cs.AI cs.CL 82%

Learning Planning-based Reasoning by Trajectories Collection and Process Reward Synthesizing

Fangkai Jiao, Chengwei Qin, Zhengyuan Liu, Nancy F. Chen, Shafiq Joty

专题命中推理与问题求解：LLM(abstract)；large language model(abstract)；language model(abstract)；preference optimization(abstract)

Comments 17 pages, 9 figures. EMNLP 2024

2410.06203 2024-10-10 cs.CL cs.AI 82%

Integrating Planning into Single-Turn Long-Form Text Generation

Yi Liang, You Wu, Honglei Zhuang, Li Chen, Jiaming Shen, Yiling Jia, Zhen Qin, Sumit Sanghai, Xuanhui Wang, Carl Yang, Michael Bendersky

专题命中推理与问题求解：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

2405.03709 2024-10-04 cs.SE cs.AI cs.LG cs.PL 82%

ScenicNL: Generating Probabilistic Scenario Programs from Natural Language

Karim Elmaaroufi, Devan Shanker, Ana Cismaru, Marcell Vazquez-Chanlatte, Alberto Sangiovanni-Vincentelli, Matei Zaharia, Sanjit A. Seshia

专题命中推理与问题求解：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

Comments 22 pages, 3 figures. Published at COLM 2024. https://ke7.github.io/ScenicNL

2410.00359 2024-10-02 cs.CL cs.AI 82%

Self-controller: Controlling LLMs with Multi-round Step-by-step Self-awareness

Xiao Peng, Xufan Geng

专题命中推理与问题求解：LLM(abstract)；large language model(abstract)；language model(abstract)；foundation model(abstract)

Comments 10 pages, 6 figures

2409.10007 2024-09-17 cs.CL cs.AI 82%

SelECT-SQL: Self-correcting ensemble Chain-of-Thought for Text-to-SQL

Ke Shen, Mayank Kejriwal

专题命中推理与问题求解：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

2404.13149 2024-08-30 cs.CL cs.AI 82%

Beyond Self-Consistency: Ensemble Reasoning Boosts Consistency and Accuracy of LLMs in Cancer Staging

Chia-Hsuan Chang, Mary M. Lucas, Yeawon Lee, Christopher C. Yang, Grace Lu-Yao

专题命中推理与问题求解：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

Comments accepted to the 22nd International Conference on Artificial Intelligence in Medicine (AIME'24)

2402.01805 2024-08-30 cs.CL cs.AI 82%

Can LLMs perform structured graph reasoning?

Palaash Agrawal, Shavak Vasania, Cheston Tan

专题命中推理与问题求解：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

Comments International Conference on Pattern Recognition (ICPR), 2024

2408.07199 2024-08-15 cs.AI cs.LG 82%

Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents

Pranav Putta, Edmund Mills, Naman Garg, Sumeet Motwani, Chelsea Finn, Divyansh Garg, Rafael Rafailov

专题命中推理与问题求解：LLM(abstract)；large language model(abstract)；language model(abstract)；preference optimization(abstract)

2408.02882 2024-08-07 cs.AI cs.CR cs.LG 82%

Compromising Embodied Agents with Contextual Backdoor Attacks

Aishan Liu, Yuguang Zhou, Xianglong Liu, Tianyuan Zhang, Siyuan Liang, Jiakai Wang, Yanjun Pu, Tianlin Li, Junqi Zhang, Wenbo Zhou, Qing Guo, Dacheng Tao

专题命中推理与问题求解：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

2407.02514 2024-08-07 cs.LO cs.AI cs.CL 82%

LOGIC-LM++: Multi-Step Refinement for Symbolic Formulations

Shashank Kirtania, Priyanshu Gupta, Arjun Radhakirshna

专题命中推理与问题求解：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

2402.14851 2024-07-12 cs.CL cs.AI cs.DB 82%

$R^3$: "This is My SQL, Are You With Me?" A Consensus-Based Multi-Agent System for Text-to-SQL Tasks

Hanchen Xia, Feng Jiang, Naihao Deng, Cunxiang Wang, Guojiang Zhao, Rada Mihalcea, Yue Zhang

专题命中推理与问题求解：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

Comments 12 pages, 2 figures, 8 tables

2407.02340 2024-07-03 cs.CL cs.AI 82%

RVISA: Reasoning and Verification for Implicit Sentiment Analysis

Wenna Lai, Haoran Xie, Guandong Xu, Qing Li

专题命中推理与问题求解：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

Comments 11 pages, 6 figures, and 4 tables

2312.02706 2024-06-27 cs.AI cs.CL 82%

Large Knowledge Model: Perspectives and Challenges

Huajun Chen

专题命中推理与问题求解：LLM(abstract)；large language model(abstract)；language model(abstract)；pretraining(abstract)

Comments Data Intelligence, Published: Jun 18, 2024

2406.14562 2024-06-21 cs.CL cs.AI cs.CV 82%

Whiteboard-of-Thought: Thinking Step-by-Step Across Modalities

Sachit Menon, Richard Zemel, Carl Vondrick

专题命中推理与问题求解：large language model(abstract)；language model(abstract)；pretraining(abstract)；prompting(abstract)

Comments Project website: whiteboard.cs.columbia.edu/

2401.02009 2024-06-10 cs.CL cs.AI 82%

Self-Contrast: Better Reflection Through Inconsistent Solving Perspectives

Wenqi Zhang, Yongliang Shen, Linjuan Wu, Qiuying Peng, Jun Wang, Yueting Zhuang, Weiming Lu

专题命中推理与问题求解：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

Comments Accepted by ACL 2024 Main

2406.02030 2024-06-06 cs.CL cs.AI 82%

Multimodal Reasoning with Multimodal Knowledge Graph

Junlin Lee, Yequan Wang, Jing Li, Min Zhang

专题命中推理与问题求解：LLM(abstract)；large language model(abstract)；language model(abstract)；pretraining(abstract)

Comments Accepted by ACL 2024 (Main Conference)

2405.05189 2024-06-04 cs.CL cs.AI 82%

MIDGARD: Self-Consistency Using Minimum Description Length for Structured Commonsense Reasoning

Inderjeet Nair, Lu Wang

专题命中推理与问题求解：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

Comments Accepted at ACL 2024(main)

2405.20902 2024-06-03 cs.CL cs.AI cs.CR 82%

Preemptive Answer "Attacks" on Chain-of-Thought Reasoning

Rongwu Xu, Zehan Qi, Wei Xu

专题命中推理与问题求解：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

Comments Accepted to ACL'24 (Findings). Camera-ready version

2405.11403 2024-05-21 cs.CL cs.AI 82%

MapCoder: Multi-Agent Code Generation for Competitive Problem Solving

Md. Ashraful Islam, Mohammed Eunus Ali, Md Rizwan Parvez

专题命中推理与问题求解：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

2404.15667 2024-05-09 cs.CL cs.AI 82%

The Promise and Challenges of Using LLMs to Accelerate the Screening Process of Systematic Reviews

Aleksi Huotala, Miikka Kuutila, Paul Ralph, Mika Mäntylä

专题命中推理与问题求解：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

Comments Accepted to the International Conference on Evaluation and Assessment in Software Engineering (EASE), 2024 edition

2403.19116 2024-03-29 cs.CL cs.AI 82%

MFORT-QA: Multi-hop Few-shot Open Rich Table Question Answering

Che Guan, Mengyu Huang, Peng Zhang

专题命中推理与问题求解：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

Comments 8 pages

2304.02496 2024-03-29 cs.CL cs.AI 82%

Evaluation of ChatGPT Family of Models for Biomedical Reasoning and Classification

Shan Chen, Yingya Li, Sheng Lu, Hoang Van, Hugo JWL Aerts, Guergana K. Savova, Danielle S. Bitterman

专题命中推理与问题求解：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

Comments 28 pages, 2 tables and 4 figures. Submitting for review

2403.09631 2024-03-15 cs.CV cs.AI cs.CL cs.RO 82%

3D-VLA: A 3D Vision-Language-Action Generative World Model

Haoyu Zhen, Xiaowen Qiu, Peihao Chen, Jincheng Yang, Xin Yan, Yilun Du, Yining Hong, Chuang Gan

专题命中推理与问题求解：LLM(abstract)；large language model(abstract)；language model(abstract)；foundation model(abstract)

Comments Project page: https://vis-www.cs.umass.edu/3dvla/

2310.08992 2024-03-15 cs.AI cs.CL cs.PL 82%

CodeChain: Towards Modular Code Generation Through Chain of Self-revisions with Representative Sub-modules

Hung Le, Hailin Chen, Amrita Saha, Akash Gokul, Doyen Sahoo, Shafiq Joty

专题命中推理与问题求解：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

Comments Accepted to ICLR 2024

2402.15420 2024-02-26 cs.RO cs.CL cs.LG 82%

PREDILECT: Preferences Delineated with Zero-Shot Language-based Reasoning in Reinforcement Learning

Simon Holk, Daniel Marta, Iolanda Leite

专题命中推理与问题求解：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

Comments 8 pages, 8 Figures, 2 Tables

2401.09414 2024-01-18 cs.CV cs.AI cs.LG cs.MM 82%

Vlogger: Make Your Dream A Vlog

Shaobin Zhuang, Kunchang Li, Xinyuan Chen, Yaohui Wang, Ziwei Liu, Yu Qiao, Yali Wang

专题命中推理与问题求解：LLM(abstract)；large language model(abstract)；language model(abstract)；foundation model(abstract)

Comments 16 pages, 8 figures, 11 tables

2305.13186 2023-10-24 cs.CL cs.AI 82%

SCITAB: A Challenging Benchmark for Compositional Reasoning and Claim Verification on Scientific Tables

Xinyuan Lu, Liangming Pan, Qian Liu, Preslav Nakov, Min-Yen Kan

专题命中推理与问题求解：large language model(abstract)；language model(abstract)；pretraining(abstract)；prompting(abstract)

Comments Accepted at EMNLP 2023 (main conference, long paper)

2307.01540 2023-09-04 cs.HC cs.AI cs.CL 82%

Learning to Prompt in the Classroom to Understand AI Limits: A pilot study

Emily Theophilou, Cansu Koyuturk, Mona Yavari, Sathya Bursic, Gregor Donabauer, Alessia Telari, Alessia Testa, Raffaele Boiano, Davinia Hernandez-Leo, Martin Ruskov, Davide Taibi, Alessandro Gabbiadini, Dimitri Ognibene

专题命中推理与问题求解：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

Comments Accepted for AIXIA 2023 22nd International Conference of the Italian Association for Artificial Intelligence 6 - 9 Nov, 2023, Rome, Italy

2212.10505 2023-05-25 cs.CL cs.AI cs.CV 82%

DePlot: One-shot visual language reasoning by plot-to-table translation

Fangyu Liu, Julian Martin Eisenschlos, Francesco Piccinno, Syrine Krichene, Chenxi Pang, Kenton Lee, Mandar Joshi, Wenhu Chen, Nigel Collier, Yasemin Altun

专题命中推理与问题求解：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

Comments ACL 2023 (Findings)

2305.14128 2023-05-24 cs.CL cs.AI 82%

Dr.ICL: Demonstration-Retrieved In-context Learning

Man Luo, Xin Xu, Zhuyun Dai, Panupong Pasupat, Mehran Kazemi, Chitta Baral, Vaiva Imbrasaite, Vincent Y Zhao

专题命中推理与问题求解：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

1. 推理与问题求解 18999 篇

Learning Planning-based Reasoning by Trajectories Collection and Process Reward Synthesizing

Integrating Planning into Single-Turn Long-Form Text Generation

ScenicNL: Generating Probabilistic Scenario Programs from Natural Language

Self-controller: Controlling LLMs with Multi-round Step-by-step Self-awareness

SelECT-SQL: Self-correcting ensemble Chain-of-Thought for Text-to-SQL

Beyond Self-Consistency: Ensemble Reasoning Boosts Consistency and Accuracy of LLMs in Cancer Staging

Can LLMs perform structured graph reasoning?

Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents

Compromising Embodied Agents with Contextual Backdoor Attacks

LOGIC-LM++: Multi-Step Refinement for Symbolic Formulations

$R^3$: "This is My SQL, Are You With Me?" A Consensus-Based Multi-Agent System for Text-to-SQL Tasks

RVISA: Reasoning and Verification for Implicit Sentiment Analysis

Large Knowledge Model: Perspectives and Challenges

Whiteboard-of-Thought: Thinking Step-by-Step Across Modalities

Self-Contrast: Better Reflection Through Inconsistent Solving Perspectives

Multimodal Reasoning with Multimodal Knowledge Graph

MIDGARD: Self-Consistency Using Minimum Description Length for Structured Commonsense Reasoning

Preemptive Answer "Attacks" on Chain-of-Thought Reasoning

MapCoder: Multi-Agent Code Generation for Competitive Problem Solving

The Promise and Challenges of Using LLMs to Accelerate the Screening Process of Systematic Reviews

MFORT-QA: Multi-hop Few-shot Open Rich Table Question Answering

Evaluation of ChatGPT Family of Models for Biomedical Reasoning and Classification

3D-VLA: A 3D Vision-Language-Action Generative World Model

CodeChain: Towards Modular Code Generation Through Chain of Self-revisions with Representative Sub-modules

PREDILECT: Preferences Delineated with Zero-Shot Language-based Reasoning in Reinforcement Learning

Vlogger: Make Your Dream A Vlog

SCITAB: A Challenging Benchmark for Compositional Reasoning and Claim Verification on Scientific Tables

Learning to Prompt in the Classroom to Understand AI Limits: A pilot study

DePlot: One-shot visual language reasoning by plot-to-table translation

Dr.ICL: Demonstration-Retrieved In-context Learning