语言大模型 / LLM - arXivDaily 专题

2304.10464 2023-12-14 cs.CL 83%

Learning to Plan with Natural Language

Yiduo Guo, Yaobo Liang, Chenfei Wu, Wenshan Wu, Dongyan Zhao, Nan Duan

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

Comments Large Language Model, Learning from feedback, Planning and Reasoning

2310.16427 2023-12-08 cs.CL 83%

PromptAgent: Strategic Planning with Language Models Enables Expert-level Prompt Optimization

Xinyuan Wang, Chenxi Li, Zhen Wang, Fan Bai, Haotian Luo, Jiayou Zhang, Nebojsa Jojic, Eric P. Xing, Zhiting Hu

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

Comments 34 pages, 10 figures

2311.09721 2023-11-17 cs.CL 83%

On Evaluating the Integration of Reasoning and Action in LLM Agents with Database Question Answering

Linyong Nan, Ellen Zhang, Weijin Zou, Yilun Zhao, Wenfei Zhou, Arman Cohan

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

2311.09277 2023-11-17 cs.CL 83%

Contrastive Chain-of-Thought Prompting

Yew Ken Chia, Guizhen Chen, Luu Anh Tuan, Soujanya Poria, Lidong Bing

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

2311.04659 2023-11-09 cs.AI 83%

Pragmatic Reasoning Unlocks Quantifier Semantics for Foundation Models

Yiyuan Li, Rakesh R. Menon, Sayan Ghosh, Shashank Srivastava

专题命中推理与问题求解：foundation model(title,abstract)；language model(abstract)；分类 cs.AI

Comments EMNLP 2023

2212.09146 2023-11-06 cs.CL 83%

Can Retriever-Augmented Language Models Reason? The Blame Game Between the Retriever and the Language Model

Parishad BehnamGhader, Santiago Miret, Siva Reddy

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

Comments Accepted in EMNLP2023 Findings

2302.04813 2023-10-19 cs.CL 83%

Explanation Selection Using Unlabeled Data for Chain-of-Thought Prompting

Xi Ye, Greg Durrett

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

Comments EMNLP 2023

2308.05095 2023-08-15 cs.CV cs.AI 83%

LayoutLLM-T2I: Eliciting Layout Guidance from LLM for Text-to-Image Generation

Leigang Qu, Shengqiong Wu, Hao Fei, Liqiang Nie, Tat-Seng Chua

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

Comments Accepted by ACM MM 2023

2307.01640 2023-07-06 cs.CL 83%

Chain of Thought Prompting Elicits Knowledge Augmentation

Dingjun Wu, Jing Zhang, Xinmei Huang

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

Comments Accepted by Findings of ACL 2023

2210.05901 2023-06-07 cs.CL 83%

Zero-Shot Prompting for Implicit Intent Prediction and Recommendation with Commonsense Reasoning

Hui-Chi Kuo, Yun-Nung Chen

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

2304.05973 2023-04-13 cs.IR cs.CL 83%

HiPrompt: Few-Shot Biomedical Knowledge Fusion via Hierarchy-Oriented Prompting

Jiaying Lu, Jiaming Shen, Bo Xiong, Wenjing Ma, Steffen Staab, Carl Yang

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

Journal ref In Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval (Short-Paper Track), 2023

2303.10845 2023-03-21 cs.CL 83%

PanGu-Σ: Towards Trillion Parameter Language Model with Sparse Heterogeneous Computing

Xiaozhe Ren, Pingyi Zhou, Xinfan Meng, Xinjing Huang, Yadao Wang, Weichao Wang, Pengfei Li, Xiaoda Zhang, Alexander Podolskiy, Grigory Arshinov, Andrey Bout, Irina Piontkovskaya, Jiansheng Wei, Xin Jiang, Teng Su, Qun Liu, Jun Yao

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

2210.01240 2023-03-03 cs.CL 83%

Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-Thought

Abulhair Saparov, He He

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

Comments Published as a conference paper at ICLR 2023

2205.11822 2022-10-26 cs.CL 83%

Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanations

Jaehun Jung, Lianhui Qin, Sean Welleck, Faeze Brahman, Chandra Bhagavatula, Ronan Le Bras, Yejin Choi

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

Comments EMNLP 2022

2203.08383 2022-10-25 cs.CL 83%

Iteratively Prompt Pre-trained Language Models for Chain of Thought

Boshi Wang, Xiang Deng, Huan Sun

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

Comments EMNLP-2022 Camera-Ready. Code will be available at https://github.com/sunlab-osu/IterPrompt

2110.08387 2022-09-30 cs.CL 83%

Generated Knowledge Prompting for Commonsense Reasoning

Jiacheng Liu, Alisa Liu, Ximing Lu, Sean Welleck, Peter West, Ronan Le Bras, Yejin Choi, Hannaneh Hajishirzi

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

Comments ACL 2022 main conference

2209.01975 2022-09-07 cs.CL 83%

Selective Annotation Makes Language Models Better Few-Shot Learners

Hongjin Su, Jungo Kasai, Chen Henry Wu, Weijia Shi, Tianlu Wang, Jiayi Xin, Rui Zhang, Mari Ostendorf, Luke Zettlemoyer, Noah A. Smith, Tao Yu

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

2205.14288 2022-05-31 cs.CL 83%

Few-shot Subgoal Planning with Language Models

Lajanugen Logeswaran, Yao Fu, Moontae Lee, Honglak Lee

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

Comments NAACL 2022

2601.05336 2026-01-12 cs.RO 83%

Intent at a Glance: Gaze-Guided Robotic Manipulation via Foundation Models

意图一目了然：通过基础模型实现的注视引导的机器人操作

Tracey Yee Hsin Tay, Xu Yan, Jonathan Ouyang, Daniel Wu, William Jiang, Jonathan Kao, Yuchen Cui

机构 * University of California, Los Angeles（加州大学洛杉矶分校）

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

AI总结 GAMMA通过结合基础模型和注视技术，实现无需特定任务训练的机器人操作自主控制，提升人机交互的直观性和可扩展性。

Comments Accepted to 2025 RSS Robot Planning in the Era of Foundation Models (FM4RoboPlan) Workshop

2510.09714 2025-10-17 cs.CL cs.AI cs.LG 83%

All Code, No Thought: Current Language Models Struggle to Reason in Ciphered Language

Shiyuan Guo, Henry Sleight, Fabien Roger

机构 * Anthropic Fellows Program（Anthropic Fellow项目）； Constellation ； Anthropic

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

Comments Version 2: updated related works section on LLM steganography

2510.02780 2025-10-06 cs.CV 83%

Reasoning Riddles: How Explainability Reveals Cognitive Limits in Vision-Language Models

Prahitha Movva

机构 * University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）

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

Journal ref COLM 2025: First Workshop on the Application of LLM Explainability to Reasoning and Planning

2510.01218 2025-10-03 cs.LG cs.AI cs.CL 83%

Control the Temperature: Selective Sampling for Diverse and High-Quality LLM Outputs

Sergey Troshin, Wafaa Mohammed, Yan Meng, Christof Monz, Antske Fokkens, Vlad Niculae

机构 * Language Technology Lab, University of Amsterdam（阿姆斯特丹大学语言技术实验室）； Computational Linguistics and Text Mining Lab, Vrije Universiteit Amsterdam（阿姆斯特丹自由大学计算语言学与文本挖掘实验室）

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

Comments Second Conference on Language Modeling, 2025

2302.00763 2023-02-03 cs.LG cs.AI cs.CL 83%

Collaborating with language models for embodied reasoning

Ishita Dasgupta, Christine Kaeser-Chen, Kenneth Marino, Arun Ahuja, Sheila Babayan, Felix Hill, Rob Fergus

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

Comments Presented at NeurIPS 2022 Language and Reinforcement Learning Workshop (best paper) and NeurIPS 2022 Foundation Models for Decision Making Workshop. 4 pages main; 14 pages total (including references and appendix); 3 figures

2608.23497 2026-08-25 cs.AI cs.CL 新提交 82%

Mitigating Reasoning-Induced Misalignment via Safety-Direction Penalty

通过安全方向惩罚缓解推理诱导的不一致性

Yipeng Zhao, Qishun Yang, Shenzhe Zhu, Shu Yang, Di Wang

机构 * University of Toronto（多伦多大学）； King Abdullah University of Science and Technology（阿卜杜拉国王科技大学）； University of Texas at Austin（德克萨斯大学奥斯汀分校）

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

AI总结针对推理微调引发LLM安全退化的RIM问题，本文提出安全方向惩罚（SDP）方法，通过定位安全决策层并惩罚安全方向位移，在Qwen2.5系列模型上实现安全与推理性能的平衡。

Comments 28 pages, 4 figures

2608.21218 2026-08-24 cs.AI cs.CL cs.IR 新提交 82%

Enhancing LLMs in Predictive Political QA with Semi-Structured Data

利用半结构化数据增强大型语言模型（LLMs）在预测性政治问答（QA）中的表现

Yinan Liu, Zihan Zhou, Zichun Jin, Xinyu Wang, Bin Wang, Xiaochun Yang

机构 * School of Computer Science and Engineering, Northeastern University（东北大学计算机科学与工程学院）

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

AI总结本研究针对预测性政治问答任务，提出双视图框架PSL，结合半结构化政治记录提取立场与结构信号，在三个真实数据集及多个LLM上均优于基线方法。

2608.16539 2026-08-18 cs.SD cs.AI cs.CL eess.AS 新提交 82%

Listen, Reason, and Segment: Aligning LALMs with Editorial Judgment for Media Chapterization

听、推理与分段：使大型音频语言模型（LALMs）与编辑判断对齐以实现媒体章节化

Tony Alex, Wish Suharitdamrong, Sara Atito, Armin Mustafa, Muhammad Awais, Philip J. B. Jackson, Jiankang Deng, Ismail Elezi

机构 * University of Surrey（萨里大学）

专题命中推理与问题求解：SFT(abstract,abstract_cn)；language model(abstract)；post-training(abstract)；分类 cs.CL、cs.AI

AI总结该研究针对LALMs在实际媒体章节化部署的不足，提出基于GRPO与CoT的AudioChaps框架，构建三类数据集，使AudioChaps-R1的平均F1较SOTA提升49个百分点，实现非结构化听觉流到结构化媒体的可靠转换。

Comments 19 pages, 9 figures, 8 tables

2602.21219 2026-08-18 cs.CL cs.AI 版本更新 82%

Reasoning-Based Personalized Generation for Users with Sparse Data

基于推理的稀疏数据用户个性化生成

Bo Ni, Branislav Kveton, Samyadeep Basu, Subhojyoti Mukherjee, Leyao Wang, Franck Dernoncourt, Sungchul Kim, Seunghyun Yoon, Zichao Wang, Ruiyi Zhang, Puneet Mathur, Jihyung Kil, Jiuxiang Gu, Nedim Lipka, Yu Wang, Ryan A. Rossi, Tyler Derr

机构 * Vanderbilt University（范德比尔特大学）； Adobe Research（Adobe研究）； Yale University（耶鲁大学）； University of Oregon（俄勒冈大学）

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

AI总结 GraSPer通过预测用户未来交互并生成文本来增强稀疏上下文中的个性化生成，提升用户个性化输出质量。

2608.12336 2026-08-14 cs.CL cs.AI 新提交 82%

StorySpark: Module-wise Evolutionary Search for Story Premise Generation

StorySpark：面向故事前提生成的模块级进化搜索

Yang Yang, Zining Zhong, Qian Cao, Jindong Li, Boyun Xu, Kaishen Yuan, Menglin Yang, Yutao Yue

机构 * The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））； Renmin University of China（中国人民大学）； Shandong University（山东大学）； Institute of Deep Perception Technology, JITRI（JITRI深度感知技术研究院）

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

AI总结针对LLM故事生成中前提构思不足的问题，提出StorySpark模块级进化搜索框架，通过优化叙事模块生成更优质的故事前提，提升下游故事质量与创意性。

Comments 26 pages, 7 figures

2608.12125 2026-08-13 cs.GT cs.AI cs.CL cs.MA 新提交 82%

Do LLMs Take Care of Their Own? Similarity Signals Can Induce Cooperation

大语言模型会照顾同类吗？相似性信号可诱导合作

Akash Kundu, Emanuel Tewolde, Ratip Emin Berker, Samuel F. Brown, Vincent Conitzer

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

AI总结该研究提出首个带分级相似性信号的LLM决策评估框架，发现不同LLM应对相似性信号差异大、数据集对诱导合作影响小等，构建的LLM-行为博弈论模型可在高相似性下支持合作均衡。

Comments 41 pages, 18 Figures, 4 Tables, 16 Listings

2607.01077 2026-08-11 cs.CL cs.LG 版本更新 82%

Message Passing Enables Efficient Reasoning

消息传递实现高效推理

Xuecheng Liu, Daman Arora, Gokul Swamy, Andrea Zanette

机构 * Carnegie Mellon University（卡内基梅隆大学）

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

AI总结提出消息传递语言模型（MPLM），通过线程间直接通信和抢占机制，在Sudoku、3-SAT和长上下文问答任务中实现比串行CoT和并行FJ更高效的推理。

Comments COLM 2026

1. 推理与问题求解 18971 篇

Learning to Plan with Natural Language

PromptAgent: Strategic Planning with Language Models Enables Expert-level Prompt Optimization

On Evaluating the Integration of Reasoning and Action in LLM Agents with Database Question Answering

Contrastive Chain-of-Thought Prompting

Pragmatic Reasoning Unlocks Quantifier Semantics for Foundation Models

Can Retriever-Augmented Language Models Reason? The Blame Game Between the Retriever and the Language Model

Explanation Selection Using Unlabeled Data for Chain-of-Thought Prompting

LayoutLLM-T2I: Eliciting Layout Guidance from LLM for Text-to-Image Generation

Chain of Thought Prompting Elicits Knowledge Augmentation

Zero-Shot Prompting for Implicit Intent Prediction and Recommendation with Commonsense Reasoning

HiPrompt: Few-Shot Biomedical Knowledge Fusion via Hierarchy-Oriented Prompting

PanGu-Σ: Towards Trillion Parameter Language Model with Sparse Heterogeneous Computing

Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-Thought

Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanations

Iteratively Prompt Pre-trained Language Models for Chain of Thought

Generated Knowledge Prompting for Commonsense Reasoning

Selective Annotation Makes Language Models Better Few-Shot Learners

Few-shot Subgoal Planning with Language Models

Intent at a Glance: Gaze-Guided Robotic Manipulation via Foundation Models

All Code, No Thought: Current Language Models Struggle to Reason in Ciphered Language

Reasoning Riddles: How Explainability Reveals Cognitive Limits in Vision-Language Models

Control the Temperature: Selective Sampling for Diverse and High-Quality LLM Outputs

Collaborating with language models for embodied reasoning

Mitigating Reasoning-Induced Misalignment via Safety-Direction Penalty

Enhancing LLMs in Predictive Political QA with Semi-Structured Data

Listen, Reason, and Segment: Aligning LALMs with Editorial Judgment for Media Chapterization

Reasoning-Based Personalized Generation for Users with Sparse Data

StorySpark: Module-wise Evolutionary Search for Story Premise Generation

Do LLMs Take Care of Their Own? Similarity Signals Can Induce Cooperation

Message Passing Enables Efficient Reasoning