语言大模型 / LLM - arXivDaily 专题

2603.03332 2026-04-20 cs.CL cs.AI cs.LG 91%

Fragile Thoughts: How Large Language Models Handle Chain-of-Thought Perturbations

脆弱的思考：大型语言模型如何处理推理链扰动

Ashwath Vaithinathan Aravindan, Mayank Kejriwal

机构 * University of Southern California（南加州大学）； Information Sciences Institute（信息科学研究所）

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

AI总结本文研究了大型语言模型在推理链扰动下的鲁棒性，通过五种扰动类型评估13种模型，发现不同扰动对模型的影响各异，模型规模在某些扰动中起到保护作用。

2509.17995 2026-04-15 cs.CL cs.AI cs.LG 91%

Variation in Verification: Understanding Verification Dynamics in Large Language Models

验证的多样性：理解大型语言模型中的验证动态

Yefan Zhou, Austin Xu, Yilun Zhou, Janvijay Singh, Jiang Gui, Shafiq Joty

机构 * Salesforce AI Research（Salesforce AI研究院）； Dartmouth College（达特茅斯学院）； University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）

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

AI总结研究大型语言模型中验证动态，分析问题难度、生成器能力及验证器生成能力三个维度，发现验证有效性与问题难度相关，优化TTS应用中的基本验证策略。

Comments ICLR 2026

2602.02842 2026-02-04 cs.AI cs.CL cs.LG 91%

Chain of Simulation: A Dual-Mode Reasoning Framework for Large Language Models with Dynamic Problem Routing

模拟链：一种用于大语言模型的双模式推理框架，具有动态问题路由

Saeid Sheikhi

机构 * Faculty of Information Technology（信息科技学院）； Electrical Engineering University of Oulu, Oulu, Finland, 90014（奥卢大学电气工程学院）

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

AI总结 CoS是一种双模式推理框架，通过动态问题路由提升大语言模型的推理能力，实现更高效的准确性和效率平衡。

2508.12495 2025-11-13 cs.CL cs.AI cs.LG 91%

Mitigating Hallucinations in Large Language Models via Causal Reasoning

Yuangang Li, Yiqing Shen, Yi Nian, Jiechao Gao, Ziyi Wang, Chenxiao Yu, Shawn Li, Jie Wang, Xiyang Hu, Yue Zhao

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

2412.15238 2025-10-28 cs.CL cs.AI cs.LG cs.MA 91%

Dipper: Diversity in Prompts for Producing Large Language Model Ensembles in Reasoning tasks

Gregory Kang Ruey Lau, Wenyang Hu, Diwen Liu, Jizhuo Chen, See-Kiong Ng, Bryan Kian Hsiang Low

机构 * National University of Singapore（新加坡国立大学）； SAP（SAP公司）

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

Comments Accepted to EMNLP 2025 Main Conference

2510.09599 2025-10-13 cs.CL cs.AI cs.LG 91%

Prompting Test-Time Scaling Is A Strong LLM Reasoning Data Augmentation

Sondos Mahmoud Bsharat, Zhiqiang Shen

机构 * MBZUAI

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

Comments Our code and data are available at https://github.com/VILA-Lab/PTTS

2505.10981 2025-08-18 cs.AI cs.CL cs.LG 91%

Rethinking the Role of Prompting Strategies in LLM Test-Time Scaling: A Perspective of Probability Theory

Yexiang Liu, Zekun Li, Zhi Fang, Nan Xu, Ran He, Tieniu Tan

机构 * MAIS, Institute of Automation, Chinese Academy of Sciences（自动化研究所，中国科学院）； School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）； University of California, Santa Barbara（加州大学圣巴巴拉分校）； Beijing Wenge Technology Co., Ltd（北京文格科技有限公司）

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

Comments ACL 2025 Outstanding Paper Award, 33 pages, 51 figures

Journal ref ACL.Volume 1: Long Papers (2025) 27962-27994

2410.05563 2025-06-25 cs.CL cs.AI cs.LG 91%

Rational Metareasoning for Large Language Models

C. Nicolò De Sabbata, Theodore R. Sumers, Badr AlKhamissi, Antoine Bosselut, Thomas L. Griffiths

机构 * Princeton University（普林斯顿大学）； EPFL（洛桑联邦理工学院）； Anthropic（Anthropic公司）

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

2506.08295 2025-06-11 cs.LG cs.AI cs.CL 91%

From Passive to Active Reasoning: Can Large Language Models Ask the Right Questions under Incomplete Information?

Zhanke Zhou, Xiao Feng, Zhaocheng Zhu, Jiangchao Yao, Sanmi Koyejo, Bo Han

机构 * TMLR Group, Department of Computer Science, Hong Kong Baptist University ； Stanford University ； Mila - Qu\'ebec AI Institute ； Cooperative Medianet Innovation Center, Shanghai Jiao Tong University

专题命中推理与问题求解：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；post-training(abstract)

Comments Accepted by ICML 2025

2410.02810 2025-04-09 cs.AI cs.CL cs.LG 91%

StateAct: Enhancing LLM Base Agents via Self-prompting and State-tracking

Nikolai Rozanov, Marek Rei

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

Comments 9 pages, 5 pages appendix, 7 figures, 5 tables

2406.02061 2025-03-06 cs.LG cs.AI cs.CL 91%

Alice in Wonderland: Simple Tasks Showing Complete Reasoning Breakdown in State-Of-the-Art Large Language Models

Marianna Nezhurina, Lucia Cipolina-Kun, Mehdi Cherti, Jenia Jitsev

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

Comments v3.0. Control experiments, further AIW problem versions, testing recent reasoning models. Short version appeared at NeurIPS Scientific Methods for Understanding Deep Learning Workshop (SciDL) 2024, https://openreview.net/forum?id=Mkl7dzjYiW

2502.15990 2025-02-27 cs.IR cs.AI cs.CL cs.LG 91%

Automated Query-Product Relevance Labeling using Large Language Models for E-commerce Search

Jayant Sachdev, Sean D Rosario, Abhijeet Phatak, He Wen, Swati Kirti, Chittaranjan Tripathy

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

2502.09390 2025-02-14 cs.CL cs.AI cs.LG 91%

SQuARE: Sequential Question Answering Reasoning Engine for Enhanced Chain-of-Thought in Large Language Models

Daniel Fleischer, Moshe Berchansky, Gad Markovits, Moshe Wasserblat

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

Comments 14 pages

2408.00764 2025-02-07 cs.CL cs.AI cs.LG 91%

AgentGen: Enhancing Planning Abilities for Large Language Model based Agent via Environment and Task Generation

Mengkang Hu, Pu Zhao, Can Xu, Qingfeng Sun, Jianguang Lou, Qingwei Lin, Ping Luo, Saravan Rajmohan

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

Comments Accepted by KDD 2025 (Research Track). Project page: https://agent-gen.github.io/

2501.18816 2025-02-03 cs.CL cs.AI cs.LG 91%

Large Language Models as Common-Sense Heuristics

Andrey Borro, Patricia J Riddle, Michael W Barley, Michael J Witbrock

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

Comments 7 page body, 2 page references, 5 page appendix (14 page total); 1 figure; Submitted to IJCAI2025

2402.11140 2025-01-08 cs.CL cs.AI cs.LG 91%

Boosting of Thoughts: Trial-and-Error Problem Solving with Large Language Models

Sijia Chen, Baochun Li, Di Niu

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

Comments Accepted as a poster paper by ICLR2024. 27 pages, 5 figures, 18 tables. [Source Code](https://github.com/iQua/llmpebase/tree/main/examples/BoTReasoning)

2501.02026 2025-01-07 cs.CL cs.AI cs.LG cs.LO 91%

Recursive Decomposition of Logical Thoughts: Framework for Superior Reasoning and Knowledge Propagation in Large Language Models

Kaleem Ullah Qasim, Jiashu Zhang, Tariq Alsahfi, Ateeq Ur Rehman Butt

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

2407.05134 2024-11-19 cs.AI cs.CL cs.LG 91%

Solving for X and Beyond: Can Large Language Models Solve Complex Math Problems with More-Than-Two Unknowns?

Kuei-Chun Kao, Ruochen Wang, Cho-Jui Hsieh

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

Journal ref https://aclanthology.org/2024.findings-emnlp.980/

2409.12618 2024-10-02 cs.CL cs.AI cs.LG cs.MA 91%

Iteration of Thought: Leveraging Inner Dialogue for Autonomous Large Language Model Reasoning

Santosh Kumar Radha, Yasamin Nouri Jelyani, Ara Ghukasyan, Oktay Goktas

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

2409.09415 2024-09-17 cs.CL cs.AI cs.LG 91%

Enhancing LLM Problem Solving with REAP: Reflection, Explicit Problem Deconstruction, and Advanced Prompting

Ryan Lingo, Martin Arroyo, Rajeev Chhajer

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

Comments 524 pages, 3 figures

2310.08582 2024-07-25 cs.CL cs.AI cs.LG cs.RO 91%

Tree-Planner: Efficient Close-loop Task Planning with Large Language Models

Mengkang Hu, Yao Mu, Xinmiao Yu, Mingyu Ding, Shiguang Wu, Wenqi Shao, Qiguang Chen, Bin Wang, Yu Qiao, Ping Luo

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

Comments Published in ICLR 2024

2306.06094 2024-07-12 cs.CV cs.AI cs.CL cs.LG 91%

Leveraging Large Language Models for Scalable Vector Graphics-Driven Image Understanding

Mu Cai, Zeyi Huang, Yuheng Li, Utkarsh Ojha, Haohan Wang, Yong Jae Lee

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

2311.09762 2024-06-25 cs.CL cs.AI cs.LG 91%

Graph Elicitation for Guiding Multi-Step Reasoning in Large Language Models

Jinyoung Park, Ameen Patel, Omar Zia Khan, Hyunwoo J. Kim, Joo-Kyung Kim

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

Comments Preprint

2401.09074 2024-06-13 cs.LG cs.AI cs.CL cs.PL 91%

Code Simulation Challenges for Large Language Models

Emanuele La Malfa, Christoph Weinhuber, Orazio Torre, Fangru Lin, Samuele Marro, Anthony Cohn, Nigel Shadbolt, Michael Wooldridge

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

Comments Code: https://github.com/EmanueleLM/CodeSimulation

2406.06588 2024-06-12 cs.CL cs.AI cs.LG cs.NE 91%

Assessing the Emergent Symbolic Reasoning Abilities of Llama Large Language Models

Flavio Petruzzellis, Alberto Testolin, Alessandro Sperduti

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

Comments Accepted at 33rd International Conference on Artificial Neural Networks (ICANN24)

2404.03204 2024-05-21 eess.AS cs.AI cs.CL cs.LG cs.SD 91%

RALL-E: Robust Codec Language Modeling with Chain-of-Thought Prompting for Text-to-Speech Synthesis

Detai Xin, Xu Tan, Kai Shen, Zeqian Ju, Dongchao Yang, Yuancheng Wang, Shinnosuke Takamichi, Hiroshi Saruwatari, Shujie Liu, Jinyu Li, Sheng Zhao

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

2405.01502 2024-05-03 cs.CL cs.AI cs.LG 91%

Analyzing the Role of Semantic Representations in the Era of Large Language Models

Zhijing Jin, Yuen Chen, Fernando Gonzalez, Jiarui Liu, Jiayi Zhang, Julian Michael, Bernhard Schölkopf, Mona Diab

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

Comments NAACL 2024

2311.04205 2024-04-22 cs.CL cs.AI cs.LG 91%

Rephrase and Respond: Let Large Language Models Ask Better Questions for Themselves

Yihe Deng, Weitong Zhang, Zixiang Chen, Quanquan Gu

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

Comments 25 pages, 7 figures, 22 tables

2308.09687 2024-04-04 cs.CL cs.AI cs.LG 91%

Graph of Thoughts: Solving Elaborate Problems with Large Language Models

Maciej Besta, Nils Blach, Ales Kubicek, Robert Gerstenberger, Michal Podstawski, Lukas Gianinazzi, Joanna Gajda, Tomasz Lehmann, Hubert Niewiadomski, Piotr Nyczyk, Torsten Hoefler

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

Journal ref Proceedings of the AAAI Conference on Artificial Intelligence 2024 (AAAI'24)

2403.12999 2024-03-21 cs.RO cs.AI cs.CL cs.LG 91%

Prompt Selection and Augmentation for Few Examples Code Generation in Large Language Model and its Application in Robotics Control

On Tai Wu, Frodo Kin Sun Chan, Zunhao Zhang, Yan Nei Law, Benny Drescher, Edmond Shiao Bun Lai

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

Comments 17 pages, 4 figures

1. 推理与问题求解 18875 篇

Fragile Thoughts: How Large Language Models Handle Chain-of-Thought Perturbations

Variation in Verification: Understanding Verification Dynamics in Large Language Models

Chain of Simulation: A Dual-Mode Reasoning Framework for Large Language Models with Dynamic Problem Routing

Mitigating Hallucinations in Large Language Models via Causal Reasoning

Dipper: Diversity in Prompts for Producing Large Language Model Ensembles in Reasoning tasks

Prompting Test-Time Scaling Is A Strong LLM Reasoning Data Augmentation

Rethinking the Role of Prompting Strategies in LLM Test-Time Scaling: A Perspective of Probability Theory

Rational Metareasoning for Large Language Models

From Passive to Active Reasoning: Can Large Language Models Ask the Right Questions under Incomplete Information?

StateAct: Enhancing LLM Base Agents via Self-prompting and State-tracking

Alice in Wonderland: Simple Tasks Showing Complete Reasoning Breakdown in State-Of-the-Art Large Language Models

Automated Query-Product Relevance Labeling using Large Language Models for E-commerce Search

SQuARE: Sequential Question Answering Reasoning Engine for Enhanced Chain-of-Thought in Large Language Models

AgentGen: Enhancing Planning Abilities for Large Language Model based Agent via Environment and Task Generation

Large Language Models as Common-Sense Heuristics

Boosting of Thoughts: Trial-and-Error Problem Solving with Large Language Models

Recursive Decomposition of Logical Thoughts: Framework for Superior Reasoning and Knowledge Propagation in Large Language Models

Solving for X and Beyond: Can Large Language Models Solve Complex Math Problems with More-Than-Two Unknowns?

Iteration of Thought: Leveraging Inner Dialogue for Autonomous Large Language Model Reasoning

Enhancing LLM Problem Solving with REAP: Reflection, Explicit Problem Deconstruction, and Advanced Prompting

Tree-Planner: Efficient Close-loop Task Planning with Large Language Models

Leveraging Large Language Models for Scalable Vector Graphics-Driven Image Understanding

Graph Elicitation for Guiding Multi-Step Reasoning in Large Language Models

Code Simulation Challenges for Large Language Models

Assessing the Emergent Symbolic Reasoning Abilities of Llama Large Language Models

RALL-E: Robust Codec Language Modeling with Chain-of-Thought Prompting for Text-to-Speech Synthesis

Analyzing the Role of Semantic Representations in the Era of Large Language Models

Rephrase and Respond: Let Large Language Models Ask Better Questions for Themselves

Graph of Thoughts: Solving Elaborate Problems with Large Language Models

Prompt Selection and Augmentation for Few Examples Code Generation in Large Language Model and its Application in Robotics Control