大模型推理能力 - arXivDaily 专题

2506.09853 2025-10-28 cs.CL cs.AI math.ST stat.ME stat.TH 90%

Causal Sufficiency and Necessity Improves Chain-of-Thought Reasoning

Xiangning Yu, Zhuohan Wang, Linyi Yang, Haoxuan Li, Anjie Liu, Xiao Xue, Jun Wang, Mengyue Yang

机构 * Tianjin University（天津大学）； City University of Hong Kong（香港城市大学）； University College London（伦敦大学学院）； Peking University（北京大学）； The Hong Kong University of Science and Technology (Guangzhou)（香港科学与技术大学（广州））； University of Bristol（布里斯托大学）

专题命中数学推理：reasoning(title,abstract)；chain-of-thought(title,abstract)；CoT(abstract)；分类 cs.CL、cs.AI

2507.00971 2025-10-28 cs.LG cs.AI 86%

Reasoning as an Adaptive Defense for Safety

Taeyoun Kim, Fahim Tajwar, Aditi Raghunathan, Aviral Kumar

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

专题命中数学推理：reasoning(title,abstract)；chain-of-thought(abstract)；test-time compute(abstract)；分类 cs.AI、cs.LG

Comments 44 pages, 10 Figures, 7 Tables

2506.19143 2025-10-28 cs.LG cs.AI cs.CL 85%

Thought Anchors: Which LLM Reasoning Steps Matter?

Paul C. Bogdan, Uzay Macar, Neel Nanda, Arthur Conmy

机构 * MATS

专题命中数学推理：reasoning(title,abstract)；planning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Paul C. Bogdan and Uzay Macar contributed equally to this work, and their listed order was determined by coinflip. Neel Nanda and Arthur Conmy contributed equally to this work as senior authors, and their listed order was determined by coinflip

2505.22453 2025-10-28 cs.CL cs.AI cs.CV cs.LG 82%

First SFT, Second RL, Third UPT: Continual Improving Multi-Modal LLM Reasoning via Unsupervised Post-Training

Lai Wei, Yuting Li, Chen Wang, Yue Wang, Linghe Kong, Weiran Huang, Lichao Sun

机构 * School of Computer Science, Shanghai Jiao Tong University（上海交通大学计算机科学学院）； Zhongguancun Academy（中关村学院）； Shanghai Innovation Institute（上海创新研究院）； Lehigh University（莱特大学）

专题命中数学推理：reasoning(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Accepted by NeurIPS 2025

2412.15238 2025-10-28 cs.CL cs.AI cs.LG cs.MA 82%

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）

专题命中数学推理：reasoning(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Accepted to EMNLP 2025 Main Conference

2510.19099 2025-10-28 cs.LG cs.AI 81%

What Makes a Good Curriculum? Disentangling the Effects of Data Ordering on LLM Mathematical Reasoning

Yaning Jia, Chunhui Zhang, Xingjian Diao, Xiangchi Yuan, Zhongyu Ouyang, Chiyu Ma, Soroush Vosoughi

机构 * Dartmouth College（达特茅斯学院）

专题命中数学推理：reasoning(title,abstract)；分类 cs.AI、cs.LG

Comments 8 pages (main text) + 4 pages (appendix), 4 figures

2506.01347 2025-10-28 cs.CL cs.LG 81%

The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning

Xinyu Zhu, Mengzhou Xia, Zhepei Wei, Wei-Lin Chen, Danqi Chen, Yu Meng

机构 * Computer Science Department, University of Virginia（弗吉尼亚大学计算机科学系）； Princeton Language and Intelligence (PLI), Princeton University（普林斯顿大学语言与智能研究所）

专题命中数学推理：reasoning(title,abstract)；分类 cs.CL、cs.LG

Comments Accepted to NeurIPS 2025

2510.22132 2025-10-28 cs.AI 79%

Controllable Mathematical Reasoning via Self-Optimizing Thought Vectors

Xuying LI

机构 * Kepler（开普勒）

专题命中数学推理：reasoning(title,abstract)；分类 cs.AI

2505.23566 2025-10-28 cs.CV 75%

Uni-MuMER: Unified Multi-Task Fine-Tuning of Vision-Language Model for Handwritten Mathematical Expression Recognition

Yu Li, Jin Jiang, Jianhua Zhu, Shuai Peng, Baole Wei, Yuxuan Zhou, Liangcai Gao

机构 * Wangxuan Institute of Computer Technology, Peking University（计算机技术研究院，北京大学）

专题命中数学推理：reasoning(abstract)；chain-of-thought(abstract)；CoT(abstract)

Comments Accepted by NeurIPS 2025 as a spotlight

2510.22852 2025-10-28 cs.LG cs.AI 62%

Encoder-Decoder Diffusion Language Models for Efficient Training and Inference

Marianne Arriola, Yair Schiff, Hao Phung, Aaron Gokaslan, Volodymyr Kuleshov

机构 * Department of Computer Science, Cornell University（计算机科学系，康奈尔大学）

专题命中数学推理：reasoning(abstract)；分类 cs.AI、cs.LG

Comments NeurIPS 2025. We provide the code at https://github.com/kuleshov-group/e2d2

2510.22798 2025-10-28 cs.CL cs.LG 62%

VEHME: A Vision-Language Model For Evaluating Handwritten Mathematics Expressions

Thu Phuong Nguyen, Duc M. Nguyen, Hyotaek Jeon, Hyunwook Lee, Hyunmin Song, Sungahn Ko, Taehwan Kim

专题命中数学推理：reasoning(abstract)；分类 cs.CL、cs.LG

Comments EMNLP 2025. Project Website: https://vehme.github.io/

2502.05605 2025-10-28 cs.CL cs.LG 62%

Evolving LLMs' Self-Refinement Capability via Synergistic Training-Inference Optimization

Yongcheng Zeng, Xinyu Cui, Xuanfa Jin, Qirui Mi, Guoqing Liu, Zexu Sun, Mengyue Yang, Dong Li, Weiyu Ma, Ning Yang, Jian Zhao, Jianye Hao, Haifeng Zhang, Jun Wang

机构 * Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）； 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 Science and Technology of China（中国科学技术大学）； Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学耿家庄人工智能学院）； University of Bristo, UK（英国布里斯托大学）； Zhongguancun Academy, China（中关村学院）； Huawei Noah’s Ark Lab, China（华为诺亚实验室）； University College London, UK（伦敦大学学院）

专题命中数学推理：reasoning(abstract)；分类 cs.CL、cs.LG

2510.21999 2025-10-28 cs.AI 57%

Foundation of Intelligence: Review of Math Word Problems from Human Cognition Perspective

Zhenya Huang, Jiayu Liu, Xin Lin, Zhiyuan Ma, Shangzi Xue, Tong Xiao, Qi Liu, Yee Whye Teh, Enhong Chen

机构 * Department of Statistics, University of Oxford（统计学系、牛津大学）

专题命中数学推理：reasoning(abstract)；分类 cs.AI

2505.21732 2025-10-28 cs.LG 57%

LaX: Boosting Low-Rank Training of Foundation Models via Latent Crossing

Ruijie Zhang, Ziyue Liu, Zhengyang Wang, Zheng Zhang

机构 * University of California at Santa Barbara（加州大学圣芭芭拉分校）

专题命中数学推理：reasoning(abstract)；分类 cs.LG

1. 数学推理 14 篇