语言大模型 / LLM - arXivDaily 专题

2404.00027 2024-10-17 cs.HC cs.AI cs.CL cs.CY cs.LG 80%

LLMs as Writing Assistants: Exploring Perspectives on Sense of Ownership and Reasoning

Azmine Toushik Wasi, Mst Rafia Islam, Raima Islam

专题命中推理与问题求解：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 5 Pages, 3 Figures. Accepted in The Third Workshop on Intelligent and Interactive Writing Assistants at CHI 2024

Journal ref The Third Workshop on Intelligent and Interactive Writing Assistants at CHI 2024

2406.18695 2024-10-10 cs.LG cs.AI cs.CL 80%

Learning to Correct for QA Reasoning with Black-box LLMs

Jaehyung Kim, Dongyoung Kim, Yiming Yang

专题命中推理与问题求解：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 22 pages; EMNLP 2024 (long, main)

2406.11911 2024-10-10 cs.AI cs.CL cs.LG 80%

A Notion of Complexity for Theory of Mind via Discrete World Models

X. Angelo Huang, Emanuele La Malfa, Samuele Marro, Andrea Asperti, Anthony Cohn, Michael Wooldridge

专题命中推理与问题求解：large language model(abstract)；language model(abstract)；prompting(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Accepted EMNLP 2024, Website https://flecart.github.io/complexity-tom-dwm

2410.03595 2024-10-07 cs.AI cs.CL cs.LG 80%

Understanding Reasoning in Chain-of-Thought from the Hopfieldian View

Lijie Hu, Liang Liu, Shu Yang, Xin Chen, Zhen Tan, Muhammad Asif Ali, Mengdi Li, Di Wang

专题命中推理与问题求解：large language model(abstract)；language model(abstract)；prompting(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 28 pages, a new version of "A Hopfieldian View-based Interpretation for Chain-of-Thought Reasoning"

2410.01943 2024-10-04 cs.LG cs.AI cs.CL cs.DB 80%

CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQL

Mohammadreza Pourreza, Hailong Li, Ruoxi Sun, Yeounoh Chung, Shayan Talaei, Gaurav Tarlok Kakkar, Yu Gan, Amin Saberi, Fatma Ozcan, Sercan O. Arik

专题命中推理与问题求解：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI、cs.LG

2409.15376 2024-09-25 cs.LG cs.AI cs.CL 80%

ControlMath: Controllable Data Generation Promotes Math Generalist Models

Nuo Chen, Ning Wu, Jianhui Chang, Jia Li

专题命中推理与问题求解：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 17 pages

2311.07466 2024-09-20 cs.CL cs.AI cs.LG 80%

On Measuring Faithfulness or Self-consistency of Natural Language Explanations

Letitia Parcalabescu, Anette Frank

专题命中推理与问题求解：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Paper accepted for publication at ACL 2024 Main (Bangkok, Thailand); 10 main paper pages, 30 appendix pages

2406.14425 2024-09-18 cs.CL cs.AI cs.LG 80%

SynDARin: Synthesising Datasets for Automated Reasoning in Low-Resource Languages

Gayane Ghazaryan, Erik Arakelyan, Pasquale Minervini, Isabelle Augenstein

专题命中推理与问题求解：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI、cs.LG

2403.07832 2024-09-10 cs.RO 80%

DeliGrasp: Inferring Object Properties with LLMs for Adaptive Grasp Policies

William Xie, Maria Valentini, Jensen Lavering, Nikolaus Correll

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

2408.10589 2024-08-21 cs.RO cs.HC 80%

Bidirectional Intent Communication: A Role for Large Foundation Models

Tim Schreiter, Rishi Hazra, Jens Rüppel, Andrey Rudenko

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

Comments 2024 33rd IEEE International Conference on Robot and Human Interactive Communication (RO-MAN), Workshop: Large Language Models in the RoMan Age

2311.09101 2024-08-20 cs.CL cs.AI cs.IR cs.LG 80%

Towards A Unified View of Answer Calibration for Multi-Step Reasoning

Shumin Deng, Ningyu Zhang, Nay Oo, Bryan Hooi

专题命中推理与问题求解：large language model(abstract)；language model(abstract)；prompting(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Accepted by NLRSE@ACL2024

2407.20990 2024-07-31 cs.AI cs.CL cs.CV cs.HC cs.LG 80%

From Feature Importance to Natural Language Explanations Using LLMs with RAG

Sule Tekkesinoglu, Lars Kunze

专题命中推理与问题求解：large language model(abstract)；language model(abstract)；foundation model(abstract)；分类 cs.CL、cs.AI、cs.LG

2407.16030 2024-07-24 cs.CL cs.AI cs.DB cs.LG 80%

Enhancing Temporal Understanding in LLMs for Semi-structured Tables

Irwin Deng, Kushagra Dixit, Vivek Gupta, Dan Roth

专题命中推理与问题求解：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Total Pages 18, Total Tables 6, Total figures 7

2310.05797 2024-07-12 cs.CL cs.AI cs.LG 80%

In-Context Explainers: Harnessing LLMs for Explaining Black Box Models

Nicholas Kroeger, Dan Ley, Satyapriya Krishna, Chirag Agarwal, Himabindu Lakkaraju

专题命中推理与问题求解：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI、cs.LG

2407.02473 2024-07-03 cs.RO 80%

Open Scene Graphs for Open World Object-Goal Navigation

Joel Loo, Zhanxin Wu, David Hsu

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

2402.06918 2024-06-27 cs.LG cs.AI cs.CL 80%

Generating Chain-of-Thoughts with a Pairwise-Comparison Approach to Searching for the Most Promising Intermediate Thought

Zhen-Yu Zhang, Siwei Han, Huaxiu Yao, Gang Niu, Masashi Sugiyama

专题命中推理与问题求解：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments ICML 2024

2310.02905 2024-06-25 cs.LG cs.AI cs.CL 80%

Use Your INSTINCT: INSTruction optimization for LLMs usIng Neural bandits Coupled with Transformers

Xiaoqiang Lin, Zhaoxuan Wu, Zhongxiang Dai, Wenyang Hu, Yao Shu, See-Kiong Ng, Patrick Jaillet, Bryan Kian Hsiang Low

专题命中推理与问题求解：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Accepted to ICML 2024

2309.13007 2024-06-25 cs.CL cs.AI cs.LG 80%

ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs

Justin Chih-Yao Chen, Swarnadeep Saha, Mohit Bansal

专题命中推理与问题求解：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments ACL 2024 (Camera-Ready)

2402.14897 2024-06-24 cs.CL cs.AI cs.LG 80%

Chain-of-Thought Unfaithfulness as Disguised Accuracy

Oliver Bentham, Nathan Stringham, Ana Marasović

专题命中推理与问题求解：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments TMLR accepted paper camera-ready version. First two authors contributed equally. 8 pages main, 13 pages appendix

2406.12255 2024-06-19 cs.CL cs.AI cs.HC cs.LG 80%

A Hopfieldian View-based Interpretation for Chain-of-Thought Reasoning

Lijie Hu, Liang Liu, Shu Yang, Xin Chen, Hongru Xiao, Mengdi Li, Pan Zhou, Muhammad Asif Ali, Di Wang

专题命中推理与问题求解：large language model(abstract)；language model(abstract)；prompting(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 21 pages

2401.06961 2024-06-11 cs.CL cs.AI cs.LG 80%

CHAMP: A Competition-level Dataset for Fine-Grained Analyses of LLMs' Mathematical Reasoning Capabilities

Yujun Mao, Yoon Kim, Yilun Zhou

专题命中推理与问题求解：large language model(abstract)；language model(abstract)；prompting(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments ACL 2024 (Findings). Project website at https://yujunmao1.github.io/CHAMP/

2402.14809 2024-06-04 cs.CL cs.AI cs.LG 80%

CriticBench: Benchmarking LLMs for Critique-Correct Reasoning

Zicheng Lin, Zhibin Gou, Tian Liang, Ruilin Luo, Haowei Liu, Yujiu Yang

专题命中推理与问题求解：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments ACL 2024 Findings

2405.11880 2024-05-21 cs.LG cs.AI cs.CL cs.CV 80%

Quantifying In-Context Reasoning Effects and Memorization Effects in LLMs

Siyu Lou, Yuntian Chen, Xiaodan Liang, Liang Lin, Quanshi Zhang

专题命中推理与问题求解：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI、cs.LG

2405.01695 2024-05-06 cs.SE 80%

Requirements-driven Slicing of Simulink Models Using LLMs

Dipeeka Luitel, Shiva Nejati, Mehrdad Sabetzadeh

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

Comments This paper will appear at the 11th International Workshop on Artificial Intelligence and Requirements Engineering (AIRE'24)

2404.00450 2024-04-05 cs.CL cs.AI cs.IR cs.LG 80%

Planning and Editing What You Retrieve for Enhanced Tool Learning

Tenghao Huang, Dongwon Jung, Muhao Chen

专题命中推理与问题求解：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments This paper is accepted at NAACL-Findings 2024

2402.02388 2024-04-02 cs.CL cs.AI cs.LG cs.SE 80%

Solution-oriented Agent-based Models Generation with Verifier-assisted Iterative In-context Learning

Tong Niu, Weihao Zhang, Rong Zhao

专题命中推理与问题求解：large language model(abstract)；language model(abstract)；prompting(abstract)；分类 cs.CL、cs.AI、cs.LG

Journal ref International Conference on Autonomous Agents and Multiagent Systems 2024

2403.18406 2024-03-28 cs.CV cs.AI cs.CL cs.LG 80%

An Image Grid Can Be Worth a Video: Zero-shot Video Question Answering Using a VLM

Wonkyun Kim, Changin Choi, Wonseok Lee, Wonjong Rhee

专题命中推理与问题求解：large language model(abstract)；language model(abstract)；foundation model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Our code is available at https://github.com/imagegridworth/IG-VLM

2310.19791 2024-03-18 cs.CL cs.AI cs.LG cs.PL 80%

LILO: Learning Interpretable Libraries by Compressing and Documenting Code

Gabriel Grand, Lionel Wong, Maddy Bowers, Theo X. Olausson, Muxin Liu, Joshua B. Tenenbaum, Jacob Andreas

专题命中推理与问题求解：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments ICLR 2024 camera-ready

2309.17428 2024-03-14 cs.CL cs.AI cs.LG 80%

CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsets

Lifan Yuan, Yangyi Chen, Xingyao Wang, Yi R. Fung, Hao Peng, Heng Ji

专题命中推理与问题求解：large language model(abstract)；language model(abstract)；prompting(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Accepted to ICLR 2024. Code is available at https://github.com/lifan-yuan/CRAFT

2403.00799 2024-03-05 cs.CL cs.AI cs.LG 80%

An Empirical Study of Data Ability Boundary in LLMs' Math Reasoning

Zui Chen, Yezeng Chen, Jiaqi Han, Zhijie Huang, Ji Qi, Yi Zhou

专题命中推理与问题求解：large language model(abstract)；language model(abstract)；SFT(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 33 pages, 5 figures

1. 推理与问题求解 19038 篇

LLMs as Writing Assistants: Exploring Perspectives on Sense of Ownership and Reasoning

Learning to Correct for QA Reasoning with Black-box LLMs

A Notion of Complexity for Theory of Mind via Discrete World Models

Understanding Reasoning in Chain-of-Thought from the Hopfieldian View

CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQL

ControlMath: Controllable Data Generation Promotes Math Generalist Models

On Measuring Faithfulness or Self-consistency of Natural Language Explanations

SynDARin: Synthesising Datasets for Automated Reasoning in Low-Resource Languages

DeliGrasp: Inferring Object Properties with LLMs for Adaptive Grasp Policies

Bidirectional Intent Communication: A Role for Large Foundation Models

Towards A Unified View of Answer Calibration for Multi-Step Reasoning

From Feature Importance to Natural Language Explanations Using LLMs with RAG

Enhancing Temporal Understanding in LLMs for Semi-structured Tables

In-Context Explainers: Harnessing LLMs for Explaining Black Box Models

Open Scene Graphs for Open World Object-Goal Navigation

Generating Chain-of-Thoughts with a Pairwise-Comparison Approach to Searching for the Most Promising Intermediate Thought

Use Your INSTINCT: INSTruction optimization for LLMs usIng Neural bandits Coupled with Transformers

ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs

Chain-of-Thought Unfaithfulness as Disguised Accuracy

A Hopfieldian View-based Interpretation for Chain-of-Thought Reasoning

CHAMP: A Competition-level Dataset for Fine-Grained Analyses of LLMs' Mathematical Reasoning Capabilities

CriticBench: Benchmarking LLMs for Critique-Correct Reasoning

Quantifying In-Context Reasoning Effects and Memorization Effects in LLMs

Requirements-driven Slicing of Simulink Models Using LLMs

Planning and Editing What You Retrieve for Enhanced Tool Learning

Solution-oriented Agent-based Models Generation with Verifier-assisted Iterative In-context Learning

An Image Grid Can Be Worth a Video: Zero-shot Video Question Answering Using a VLM

LILO: Learning Interpretable Libraries by Compressing and Documenting Code

CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsets

An Empirical Study of Data Ability Boundary in LLMs' Math Reasoning