语言大模型 / LLM - arXivDaily 专题

2310.06272 2024-02-27 cs.CL cs.AI cs.LG 80%

Let Models Speak Ciphers: Multiagent Debate through Embeddings

Chau Pham, Boyi Liu, Yingxiang Yang, Zhengyu Chen, Tianyi Liu, Jianbo Yuan, Bryan A. Plummer, Zhaoran Wang, Hongxia 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 Accepted to ICLR 2024

2401.09083 2024-01-18 cs.CV 80%

Remote Sensing ChatGPT: Solving Remote Sensing Tasks with ChatGPT and Visual Models

Haonan Guo, Xin Su, Chen Wu, Bo Du, Liangpei Zhang, Deren Li

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

Comments The manuscript is submitted to IEEE International Geoscience and Remote Sensing Symposium(IGARSS2024). Looking forward to seeing you in July!

2311.17842 2023-12-27 cs.RO cs.AI cs.CL cs.CV cs.LG 80%

Look Before You Leap: Unveiling the Power of GPT-4V in Robotic Vision-Language Planning

Yingdong Hu, Fanqi Lin, Tong Zhang, Li Yi, Yang Gao

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 arXiv v2: add appendix

2308.15452 2023-12-19 cs.CL cs.AI cs.LG cs.SE 80%

When Do Program-of-Thoughts Work for Reasoning?

Zhen Bi, Ningyu Zhang, Yinuo Jiang, Shumin Deng, Guozhou Zheng, Huajun Chen

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 AAAI 2024

2312.06820 2023-12-13 cs.AI cs.CL cs.LG stat.ME 80%

Extracting Self-Consistent Causal Insights from Users Feedback with LLMs and In-context Learning

Sara Abdali, Anjali Parikh, Steve Lim, Emre Kiciman

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

2305.17390 2023-12-07 cs.CL cs.AI cs.LG cs.MA cs.RO 80%

SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks

Bill Yuchen Lin, Yicheng Fu, Karina Yang, Faeze Brahman, Shiyu Huang, Chandra Bhagavatula, Prithviraj Ammanabrolu, Yejin Choi, Xiang Ren

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 NeurIPS 2023 (spotlight). Project website: https://swiftsage.github.io

2312.02179 2023-12-06 cs.LG cs.AI cs.CL 80%

Training Chain-of-Thought via Latent-Variable Inference

Du Phan, Matthew D. Hoffman, David Dohan, Sholto Douglas, Tuan Anh Le, Aaron Parisi, Pavel Sountsov, Charles Sutton, Sharad Vikram, Rif A. Saurous

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 23 pages, 37th Conference on Neural Information Processing Systems (NeurIPS 2023)

2303.17580 2023-12-05 cs.CL cs.AI cs.CV cs.LG 80%

HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face

Yongliang Shen, Kaitao Song, Xu Tan, Dongsheng Li, Weiming Lu, Yueting Zhuang

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

2312.00763 2023-12-04 cs.HC cs.AI cs.CL cs.LG 80%

Beyond ChatBots: ExploreLLM for Structured Thoughts and Personalized Model Responses

Xiao Ma, Swaroop Mishra, Ariel Liu, Sophie Su, Jilin Chen, Chinmay Kulkarni, Heng-Tze Cheng, Quoc Le, Ed Chi

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 19 pages, 11 figures

2311.18775 2023-12-01 cs.CV cs.AI cs.CL cs.LG cs.SD eess.AS 80%

CoDi-2: In-Context, Interleaved, and Interactive Any-to-Any Generation

Zineng Tang, Ziyi Yang, Mahmoud Khademi, Yang Liu, Chenguang Zhu, Mohit Bansal

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 Project Page: https://codi-2.github.io/

2305.00633 2023-10-27 cs.CL cs.AI cs.LG 80%

Self-Evaluation Guided Beam Search for Reasoning

Yuxi Xie, Kenji Kawaguchi, Yiran Zhao, Xu Zhao, Min-Yen Kan, Junxian He, Qizhe Xie

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 NeurIPS 2023. 10 pages, 7 figures, 4 tables (33 pages, 14 figures, 15 tables including references and appendices)

2308.00436 2023-10-06 cs.AI cs.CL cs.LG 80%

SelfCheck: Using LLMs to Zero-Shot Check Their Own Step-by-Step Reasoning

Ning Miao, Yee Whye Teh, Tom Rainforth

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

2306.03872 2023-10-05 cs.CL cs.AI cs.LG 80%

Deductive Verification of Chain-of-Thought Reasoning

Zhan Ling, Yunhao Fang, Xuanlin Li, Zhiao Huang, Mingu Lee, Roland Memisevic, Hao Su

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 Published at NeurIPS 2023

2307.12057 2023-08-29 cs.CL cs.AI cs.LG 80%

External Reasoning: Towards Multi-Large-Language-Models Interchangeable Assistance with Human Feedback

Akide Liu

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 technical report, add code link. arXiv admin note: text overlap with arXiv:2305.11206 by other authors

2308.05177 2023-08-11 cs.SE cs.PL 80%

Fixing Rust Compilation Errors using LLMs

Pantazis Deligiannis, Akash Lal, Nikita Mehrotra, Aseem Rastogi

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

2307.11768 2023-07-26 cs.CL cs.AI cs.LG 80%

Question Decomposition Improves the Faithfulness of Model-Generated Reasoning

Ansh Radhakrishnan, Karina Nguyen, Anna Chen, Carol Chen, Carson Denison, Danny Hernandez, Esin Durmus, Evan Hubinger, Jackson Kernion, Kamilė Lukošiūtė, Newton Cheng, Nicholas Joseph, Nicholas Schiefer, Oliver Rausch, Sam McCandlish, Sheer El Showk, Tamera Lanham, Tim Maxwell, Venkatesa Chandrasekaran, Zac Hatfield-Dodds, Jared Kaplan, Jan Brauner, Samuel R. Bowman, Ethan Perez

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 For few-shot examples and prompts, see https://github.com/anthropics/DecompositionFaithfulnessPaper

2306.07536 2023-06-14 cs.LG cs.AI cs.CL 80%

TART: A plug-and-play Transformer module for task-agnostic reasoning

Kush Bhatia, Avanika Narayan, Christopher De Sa, Christopher Ré

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

2304.11257 2023-04-25 cs.CL cs.AI cs.LG 80%

Who's the Best Detective? LLMs vs. MLs in Detecting Incoherent Fourth Grade Math Answers

Felipe Urrutia, Roberto Araya

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

2212.08607 2022-12-19 cs.CL cs.AI cs.LG 80%

MURMUR: Modular Multi-Step Reasoning for Semi-Structured Data-to-Text Generation

Swarnadeep Saha, Xinyan Velocity Yu, Mohit Bansal, Ramakanth Pasunuru, Asli Celikyilmaz

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 22 pages (9 figures, 18 tables)

2211.09066 2022-11-17 cs.LG cs.AI cs.CL 80%

Teaching Algorithmic Reasoning via In-context Learning

Hattie Zhou, Azade Nova, Hugo Larochelle, Aaron Courville, Behnam Neyshabur, Hanie Sedghi

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

2209.07686 2022-10-17 cs.CL cs.AI cs.LG 80%

Text and Patterns: For Effective Chain of Thought, It Takes Two to Tango

Aman Madaan, Amir Yazdanbakhsh

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 Shortened version with additional results from CODEX and GPT-3. The authors contributed equally. Work done when Aman Madaan was a student researcher at Google Research, Brain Team

2204.00598 2022-05-30 cs.CV cs.AI cs.CL cs.LG 80%

Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language

Andy Zeng, Maria Attarian, Brian Ichter, Krzysztof Choromanski, Adrian Wong, Stefan Welker, Federico Tombari, Aveek Purohit, Michael Ryoo, Vikas Sindhwani, Johnny Lee, Vincent Vanhoucke, Pete Florence

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 https://socraticmodels.github.io/

2605.02909 2026-08-18 cs.LG cs.AI 版本更新 80%

Delay, Plateau, or Collapse: Evaluating the Impact of Systematic Verification Error on RLVR

延迟、平台期或崩溃：评估系统性验证错误对RLVR的影响

Kazuki Egashira, Mark Vero, Jasper Dekoninck, Florian E. Dorner, Robin Staab, Martin Vechev

机构 * ETH Zurich（苏黎世联邦理工学院）； Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）

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

AI总结本研究探究系统性验证错误对RLVR的影响，发现系统性误报会引发次优平台期或性能崩溃，验证器质量需结合错误模式而非仅样本级错误率评估。

Comments COLM 2026. Code: https://github.com/eth-sri/llm-verifier-noise

2410.14702 2026-05-12 cs.AI cs.CL 80%

Polymath: A Challenging Multi-modal Mathematical Reasoning Benchmark

PolyMATH：一个具有挑战性的多模态数学推理基准

Himanshu Gupta, Shreyas Verma, Ujjwala Anantheswaran, Kevin Scaria, Mihir Parmar, Swaroop Mishra, Chitta Baral

机构 * Arizona State University（亚利桑那州立大学）； Georgia Institute of Technology（佐治亚理工学院）

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

AI总结 PolyMATH基准通过5000张高质量图像评估多模态大语言模型的推理能力，揭示其在空间关系和抽象推理上的不足，指出模型无法真正理解视觉信息，存在逻辑错误风险。

Comments Accepted in Neural Information Processing Systems (NeurIPS 2025) Workshop: Foundations of Reasoning in Language Models

2508.06671 2025-08-13 cs.CL cs.AI 80%

Do Biased Models Have Biased Thoughts?

Swati Rajwal, Shivank Garg, Reem Abdel-Salam, Abdelrahman Zayed

机构 * Emory University（埃默里大学）； Indian Institute of Technology Roorkee（印度理工学院罗里克分校）； Cairo University（开罗大学）； Mila - Quebec AI Institute（魁北克人工智能研究所）； Polytechnique Montréal（蒙特利尔理工学院）； Amazon（亚马逊）

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

Comments Accepted at main track of the Second Conference on Language Modeling (COLM 2025)

2505.03786 2025-05-08 cs.LG cs.CL 80%

When Reasoning Beats Scale: A 1.5B Reasoning Model Outranks 13B LLMs as Discriminator

Md Fahim Anjum

机构 * Department of Neurology University of California San Francisco（神经病学系，加州大学旧金山分校）

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

Comments 12 pages, 5 figures. Code available at: https://github.com/MDFahimAnjum/llm-planning-with-reasoning

2412.12881 2024-12-18 cs.CL cs.AI 80%

RAG-Star: Enhancing Deliberative Reasoning with Retrieval Augmented Verification and Refinement

Jinhao Jiang, Jiayi Chen, Junyi Li, Ruiyang Ren, Shijie Wang, Wayne Xin Zhao, Yang Song, Tao Zhang

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

Comments LLM;RAG;MCTS

2310.00280 2024-08-22 cs.AI cs.CL 80%

Corex: Pushing the Boundaries of Complex Reasoning through Multi-Model Collaboration

Qiushi Sun, Zhangyue Yin, Xiang Li, Zhiyong Wu, Xipeng Qiu, Lingpeng Kong

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

Comments COLM 2024 / ICLR 2024 Workshop on LLM Agents

2404.07677 2024-06-05 cs.CL cs.AI 80%

ODA: Observation-Driven Agent for integrating LLMs and Knowledge Graphs

Lei Sun, Zhengwei Tao, Youdi Li, Hiroshi Arakawa

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

Comments LLM+KG

2405.17533 2024-05-29 cs.AI cs.CV cs.LG 80%

PAE: LLM-based Product Attribute Extraction for E-Commerce Fashion Trends

Apurva Sinha, Ekta Gujral

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

Comments Attribute Extraction, PDF files, Bert Embedding, Hashtag, Large Language Model (LLM), Text and Images

1. 推理与问题求解 19038 篇

Let Models Speak Ciphers: Multiagent Debate through Embeddings

Remote Sensing ChatGPT: Solving Remote Sensing Tasks with ChatGPT and Visual Models

Look Before You Leap: Unveiling the Power of GPT-4V in Robotic Vision-Language Planning

When Do Program-of-Thoughts Work for Reasoning?

Extracting Self-Consistent Causal Insights from Users Feedback with LLMs and In-context Learning

SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks

Training Chain-of-Thought via Latent-Variable Inference

HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face

Beyond ChatBots: ExploreLLM for Structured Thoughts and Personalized Model Responses

CoDi-2: In-Context, Interleaved, and Interactive Any-to-Any Generation

Self-Evaluation Guided Beam Search for Reasoning

SelfCheck: Using LLMs to Zero-Shot Check Their Own Step-by-Step Reasoning

Deductive Verification of Chain-of-Thought Reasoning

External Reasoning: Towards Multi-Large-Language-Models Interchangeable Assistance with Human Feedback

Fixing Rust Compilation Errors using LLMs

Question Decomposition Improves the Faithfulness of Model-Generated Reasoning

TART: A plug-and-play Transformer module for task-agnostic reasoning

Who's the Best Detective? LLMs vs. MLs in Detecting Incoherent Fourth Grade Math Answers

MURMUR: Modular Multi-Step Reasoning for Semi-Structured Data-to-Text Generation

Teaching Algorithmic Reasoning via In-context Learning

Text and Patterns: For Effective Chain of Thought, It Takes Two to Tango

Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language

Delay, Plateau, or Collapse: Evaluating the Impact of Systematic Verification Error on RLVR

Polymath: A Challenging Multi-modal Mathematical Reasoning Benchmark

Do Biased Models Have Biased Thoughts?

When Reasoning Beats Scale: A 1.5B Reasoning Model Outranks 13B LLMs as Discriminator

RAG-Star: Enhancing Deliberative Reasoning with Retrieval Augmented Verification and Refinement

Corex: Pushing the Boundaries of Complex Reasoning through Multi-Model Collaboration

ODA: Observation-Driven Agent for integrating LLMs and Knowledge Graphs

PAE: LLM-based Product Attribute Extraction for E-Commerce Fashion Trends