语言大模型 / LLM - arXivDaily 专题

2406.11698 2024-06-18 cs.CL 90%

Meta Reasoning for Large Language Models

Peizhong Gao, Ao Xie, Shaoguang Mao, Wenshan Wu, Yan Xia, Haipeng Mi, Furu Wei

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

2310.13571 2024-06-07 cs.CL 90%

Why Can Large Language Models Generate Correct Chain-of-Thoughts?

Rasul Tutunov, Antoine Grosnit, Juliusz Ziomek, Jun Wang, Haitham Bou-Ammar

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

2306.06427 2024-06-04 cs.CL 90%

Boosting Language Models Reasoning with Chain-of-Knowledge Prompting

Jianing Wang, Qiushi Sun, Xiang Li, Ming Gao

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

Comments ACL 2024

2404.15845 2024-04-25 cs.CL 90%

Exploring LLM Prompting Strategies for Joint Essay Scoring and Feedback Generation

Maja Stahl, Leon Biermann, Andreas Nehring, Henning Wachsmuth

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 Accepted to BEA Workshop 2024

2404.02893 2024-04-04 cs.CL 90%

ChatGLM-Math: Improving Math Problem-Solving in Large Language Models with a Self-Critique Pipeline

Yifan Xu, Xiao Liu, Xinghan Liu, Zhenyu Hou, Yueyan Li, Xiaohan Zhang, Zihan Wang, Aohan Zeng, Zhengxiao Du, Wenyi Zhao, Jie Tang, Yuxiao Dong

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

2307.07697 2024-03-26 cs.CL 90%

Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph

Jiashuo Sun, Chengjin Xu, Lumingyuan Tang, Saizhuo Wang, Chen Lin, Yeyun Gong, Lionel M. Ni, Heung-Yeung Shum, Jian Guo

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 by ICLR 2024

2403.03558 2024-03-07 cs.CL 90%

Benchmarking Hallucination in Large Language Models based on Unanswerable Math Word Problem

Yuhong Sun, Zhangyue Yin, Qipeng Guo, Jiawen Wu, Xipeng Qiu, Hui Zhao

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

Comments 11 pages, 8 figures, accepted by LREC-Coling 2024

2312.13557 2023-12-22 cs.IR cs.AI 90%

Empowering Few-Shot Recommender Systems with Large Language Models -- Enhanced Representations

Zhoumeng Wang

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 10 pages

2311.12065 2023-11-22 cs.CV cs.AI 90%

Few-Shot Classification & Segmentation Using Large Language Models Agent

Tian Meng, Yang Tao, Wuliang Yin

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

2310.14420 2023-11-07 cs.AI 90%

Monte Carlo Thought Search: Large Language Model Querying for Complex Scientific Reasoning in Catalyst Design

Henry W. Sprueill, Carl Edwards, Mariefel V. Olarte, Udishnu Sanyal, Heng Ji, Sutanay Choudhury

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 In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP2023) Findings

2305.14909 2023-11-03 cs.AI 90%

Leveraging Pre-trained Large Language Models to Construct and Utilize World Models for Model-based Task Planning

Lin Guan, Karthik Valmeekam, Sarath Sreedharan, Subbarao Kambhampati

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 NeurIPS 2023

2310.16436 2023-10-27 cs.CV cs.CL 90%

DDCoT: Duty-Distinct Chain-of-Thought Prompting for Multimodal Reasoning in Language Models

Ge Zheng, Bin Yang, Jiajin Tang, Hong-Yu Zhou, Sibei Yang

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

Comments 24 pages, 13 figures, to be published in NeurIPS 2023

2310.15166 2023-10-24 cs.CV cs.CL 90%

Large Language Models are Visual Reasoning Coordinators

Liangyu Chen, Bo Li, Sheng Shen, Jingkang Yang, Chunyuan Li, Kurt Keutzer, Trevor Darrell, Ziwei Liu

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 at NeurIPS 2023

2308.01684 2023-10-24 cs.CL 90%

Baby's CoThought: Leveraging Large Language Models for Enhanced Reasoning in Compact Models

Zheyu Zhang, Han Yang, Bolei Ma, David Rügamer, Ercong Nie

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 CoNLL 2023 BabyLM Challenge

2310.13002 2023-10-23 cs.CL 90%

Are Large Language Models Geospatially Knowledgeable?

Prabin Bhandari, Antonios Anastasopoulos, Dieter Pfoser

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

2309.15630 2023-10-20 cs.CL 90%

NLPBench: Evaluating Large Language Models on Solving NLP Problems

Linxin Song, Jieyu Zhang, Lechao Cheng, Pengyuan Zhou, Tianyi Zhou, Irene Li

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

2308.09830 2023-09-29 cs.AI 90%

Synergistic Integration of Large Language Models and Cognitive Architectures for Robust AI: An Exploratory Analysis

Oscar J. Romero, John Zimmerman, Aaron Steinfeld, Anthony Tomasic

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 AAAI 2023 Fall Symposium

2308.01825 2023-09-14 cs.CL 90%

Scaling Relationship on Learning Mathematical Reasoning with Large Language Models

Zheng Yuan, Hongyi Yuan, Chengpeng Li, Guanting Dong, Keming Lu, Chuanqi Tan, Chang Zhou, Jingren Zhou

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

Comments Working in Progress

2306.00108 2023-08-21 cs.SE cs.LG 90%

Better patching using LLM prompting, via Self-Consistency

Toufique Ahmed, Premkumar Devanbu

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 Accepted at ASE-NIER (2023) track

2210.01293 2023-06-05 cs.CL 90%

ThinkSum: Probabilistic reasoning over sets using large language models

Batu Ozturkler, Nikolay Malkin, Zhen Wang, Nebojsa Jojic

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 ACL 2023

2303.09014 2023-03-17 cs.CL 90%

ART: Automatic multi-step reasoning and tool-use for large language models

Bhargavi Paranjape, Scott Lundberg, Sameer Singh, Hannaneh Hajishirzi, Luke Zettlemoyer, Marco Tulio Ribeiro

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

2210.11610 2022-10-26 cs.CL 90%

Large Language Models Can Self-Improve

Jiaxin Huang, Shixiang Shane Gu, Le Hou, Yuexin Wu, Xuezhi Wang, Hongkun Yu, Jiawei Han

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

2210.06726 2022-10-14 cs.CL 90%

Explanations from Large Language Models Make Small Reasoners Better

Shiyang Li, Jianshu Chen, Yelong Shen, Zhiyu Chen, Xinlu Zhang, Zekun Li, Hong Wang, Jing Qian, Baolin Peng, Yi Mao, Wenhu Chen, Xifeng Yan

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

2604.09638 2026-05-28 cs.CY 90%

A Methodological Guide on Using Large Language Models for Reproducible Text Annotation in the Social Sciences and Humanities with Python and R

使用大型语言模型进行社会科学和人文学科可重复文本注释的方法论指南：基于Python和R

Qixiang Fang, Javier Garcia Bernardo, Erik-Jan van Kesteren

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

AI总结本文提供了一步一步的方法论指南，指导社会科学和人文学科研究者使用大型语言模型进行文本注释，包括设置项目、编程交互、提示设计、统计整合和可重复性管理，并附有Python和R代码示例。

Comments Accompanying Python and R notebooks are available at https://github.com/sodascience/workshop_llm_data_collection or https://zenodo.org/records/20073016

2602.06176 2026-02-09 cs.AI cs.CL cs.LG 90%

Large Language Model Reasoning Failures

大语言模型推理失败

Peiyang Song, Pengrui Han, Noah Goodman

机构 * California Institute of Technology（加州理工学院）； Stanford University（斯坦福大学）； Carleton College（卡尔顿学院）

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

AI总结本文首次系统调查大语言模型推理失败问题，提出分类框架并分析其根本原因，旨在提升模型的推理能力与鲁棒性。

Comments Repository: https://github.com/Peiyang-Song/Awesome-LLM-Reasoning-Failures. Published at TMLR 2026 with Survey Certification

2305.10601 2023-12-05 cs.CL cs.AI cs.LG 90%

Tree of Thoughts: Deliberate Problem Solving with Large Language Models

Shunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran, Thomas L. Griffiths, Yuan Cao, Karthik Narasimhan

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

Comments NeurIPS 2023 camera ready version. Code repo with all prompts: https://github.com/princeton-nlp/tree-of-thought-llm

2608.18795 2026-08-20 cs.CL cs.AI 新提交 90%

Decomposing Wrong-Consensus Agreement in LLM Self-Consistency: A GPT-4.1 Case Study

分解LLM自一致性中的错误共识一致性：GPT-4.1案例研究

Lizhuo Zhang, Mengmeng Tang, Chenfeng Long, Xiaoyong Tang, Xiang Luo

机构 * College of Information and Intelligence, Hunan Agricultural University（湖南农业大学信息与智能科学学院）； Yuelushan Laboratory（岳麓山实验室）

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

AI总结本研究以GPT-4.1为案例，将LLM自一致性的错误共识一致性分解为机械成分与偏好残差，发现难题上存在自一致性反效果，一致性为分级证据，未提出新投票方法。

Comments 18 pages, 2 figures, 9 tables; quantitative kappa-decomposition of agreement saturation in self-consistency;

2608.03502 2026-08-20 cs.AI cs.LG cs.MA 版本更新 90%

Hybrid LLM-Augmented Reinforcement Learning Agents for Complex Sequential Decision Tasks

用于复杂序列决策任务的混合大语言模型增强强化学习智能体

Christophe D. Hounwanou, John Emeka Eze, Yaé Ulrich Gaba

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

AI总结本文提出混合LLM增强RL智能体，融合LLM规划与RL动作优化，经实验验证其在序列决策任务上优于仅RL、仅LLM的基线方法，为构建更强自主系统提供了新方向。

Comments This submission is withdrawn because the uploaded manuscript does not accurately reflect the intended structure or results. Several components referenced in the text are incomplete or not represented in the PDF, and the current version may mislead readers. The work is therefore withdrawn to maintain clarity of the record

2608.17644 2026-08-19 cs.AI cs.CL 新提交 90%

LLM-Derived Preference Judgments Are Not Self-Consistent

大语言模型（LLM）得出的偏好判断不具备自一致性

Matthew T. Ford, Francis Bahk, Jingjing Wang, Adam S. Jovine, Tinghan Ye, David B. Shmoys, Peter I. Frazier

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

AI总结研究发现，用于解读人类偏好的LLM得出的数值化偏好判断存在大量持续不一致性，无法由单一效用函数概括，打破了相关研究的自一致性假设。

Comments 16 pages, 4 figures; includes appendices

2608.13315 2026-08-14 cs.GT cs.AI cs.LG cs.SY eess.SY 新提交 90%

Keep, Customize, or Exit: Default Design and Token Pricing in LLM Reasoning Services

保留、定制还是退出：大语言模型推理服务中的默认设计与代币定价

Ahmet Bugra Gundogan, Yigit Turkmen, Melih Bastopcu

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

AI总结该研究针对LLM推理服务的供需交互建立Stackelberg博弈模型，推导最优解，明确默认设置的影响条件，实验验证模型并展示均衡相关因素。

1. 推理与问题求解 18875 篇

Meta Reasoning for Large Language Models

Why Can Large Language Models Generate Correct Chain-of-Thoughts?

Boosting Language Models Reasoning with Chain-of-Knowledge Prompting

Exploring LLM Prompting Strategies for Joint Essay Scoring and Feedback Generation

ChatGLM-Math: Improving Math Problem-Solving in Large Language Models with a Self-Critique Pipeline

Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph

Benchmarking Hallucination in Large Language Models based on Unanswerable Math Word Problem

Empowering Few-Shot Recommender Systems with Large Language Models -- Enhanced Representations

Few-Shot Classification & Segmentation Using Large Language Models Agent

Monte Carlo Thought Search: Large Language Model Querying for Complex Scientific Reasoning in Catalyst Design

Leveraging Pre-trained Large Language Models to Construct and Utilize World Models for Model-based Task Planning

DDCoT: Duty-Distinct Chain-of-Thought Prompting for Multimodal Reasoning in Language Models

Large Language Models are Visual Reasoning Coordinators

Baby's CoThought: Leveraging Large Language Models for Enhanced Reasoning in Compact Models

Are Large Language Models Geospatially Knowledgeable?

NLPBench: Evaluating Large Language Models on Solving NLP Problems

Synergistic Integration of Large Language Models and Cognitive Architectures for Robust AI: An Exploratory Analysis

Scaling Relationship on Learning Mathematical Reasoning with Large Language Models

Better patching using LLM prompting, via Self-Consistency

ThinkSum: Probabilistic reasoning over sets using large language models

ART: Automatic multi-step reasoning and tool-use for large language models

Large Language Models Can Self-Improve

Explanations from Large Language Models Make Small Reasoners Better

A Methodological Guide on Using Large Language Models for Reproducible Text Annotation in the Social Sciences and Humanities with Python and R

Large Language Model Reasoning Failures

Tree of Thoughts: Deliberate Problem Solving with Large Language Models

Decomposing Wrong-Consensus Agreement in LLM Self-Consistency: A GPT-4.1 Case Study

Hybrid LLM-Augmented Reinforcement Learning Agents for Complex Sequential Decision Tasks

LLM-Derived Preference Judgments Are Not Self-Consistent

Keep, Customize, or Exit: Default Design and Token Pricing in LLM Reasoning Services