大模型推理能力

Weakest Link in the Chain: Security Vulnerabilities in Advanced Reasoning Models

Arjun Krishna, Aaditya Rastogi, Erick Galinkin

机构 * University of Waterloo（滑铁卢大学） ； NVIDIA（NVIDIA公司） 纠错

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

Comments Accepted to LLMSEC 2025

Can reasoning models comprehend mathematical problems in Chinese ancient texts? An empirical study based on data from Suanjing Shishu

Chang Liu, Dongbo Wang, Liu liu, Zhixiao Zhao

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

Comments 29pages, 7 figures

Assessing Dialect Fairness and Robustness of Large Language Models in Reasoning Tasks

Fangru Lin, Shaoguang Mao, Emanuele La Malfa, Valentin Hofmann, Adrian de Wynter, Xun Wang, Si-Qing Chen, Michael Wooldridge, Janet B. Pierrehumbert, Furu Wei

机构 * University of Oxford（牛津大学） ； Microsoft Research（微软研究院） ； The Alan Turing Institute（艾伦·图灵研究所） ； Allen Institute for AI（人工智能研究所） ； University of Washington（华盛顿大学） ； Microsoft Corporation（微软公司） ； University of York（约克大学） 纠错

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

Comments ACL 2025 main

Unleashing the Reasoning Potential of Pre-trained LLMs by Critique Fine-Tuning on One Problem

Yubo Wang, Ping Nie, Kai Zou, Lijun Wu, Wenhu Chen

机构 * University of Waterloo（滑铁卢大学） ； Vector Institute（向量研究所） ； Shanghai AI Lab（上海人工智能实验室） 纠错

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

Acting Less is Reasoning More! Teaching Model to Act Efficiently

Hongru Wang, Cheng Qian, Wanjun Zhong, Xiusi Chen, Jiahao Qiu, Shijue Huang, Bowen Jin, Mengdi Wang, Kam-Fai Wong, Heng Ji

机构 * The Chinese University of Hong Kong（香港中文大学） ； University of Illinois Urbana-Champaign（伊利诺伊大学厄巴娜-香槟分校） ； Princeton University（普林斯顿大学） ； Sun Yat-sen University（中山大学） ； Hong Kong University of Science and Technology（香港科学理工大学） 纠错

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

RaaS: Reasoning-Aware Attention Sparsity for Efficient LLM Reasoning

Junhao Hu, Wenrui Huang, Weidong Wang, Zhenwen Li, Tiancheng Hu, Zhixia Liu, Xusheng Chen, Tao Xie, Yizhou Shan

机构 * SCS, Peking University, Beijing, China（北京大学计算机科学系） ； Key Lab of HCST (PKU), MOE, Beijing, China（北京大学高校计算机科学与技术关键实验室） ； School of Computer Science, Nanjing University, Nanjing, China（南京大学计算机科学系） ； Huawei Cloud, Shanghai, China（华为云） 纠错

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

Accelerating RL for LLM Reasoning with Optimal Advantage Regression

Kianté Brantley, Mingyu Chen, Zhaolin Gao, Jason D. Lee, Wen Sun, Wenhao Zhan, Xuezhou Zhang

机构 * Harvard University（哈佛大学） ； Boston University（波士顿大学） ； Cornell University（康奈尔大学） ； Princeton University（普林斯顿大学） 纠错

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

Unleashing LLM Reasoning Capability via Scalable Question Synthesis from Scratch

Yuyang Ding, Xinyu Shi, Xiaobo Liang, Juntao Li, Zhaopeng Tu, Qiaoming Zhu, Min Zhang

机构 * Soochow University（苏州大学） ； Tencent AI Lab（腾讯AI实验室） 纠错

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

Comments ACL 2025

Safety Through Reasoning: An Empirical Study of Reasoning Guardrail Models

Makesh Narsimhan Sreedhar, Traian Rebedea, Christopher Parisien

机构 * NVIDIA Santa Clara, CA（NVIDIA圣克拉拉分校） 纠错

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

Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models

Tingchen Fu, Jiawei Gu, Yafu Li, Xiaoye Qu, Yu Cheng

机构 * Renmin University of China（中国人民大学） ； Shanghai AI Laboratory（上海人工智能实验室） ； The Chinese University of Hong Kong（香港中文大学） 纠错

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

Conformal Language Model Reasoning with Coherent Factuality

Maxon Rubin-Toles, Maya Gambhir, Keshav Ramji, Aaron Roth, Surbhi Goel

机构 * University of Pennsylvania（宾夕法尼亚大学） ； IBM Research AI（IBM人工智能研究） 纠错

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

DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning

Zhiwei He, Tian Liang, Jiahao Xu, Qiuzhi Liu, Xingyu Chen, Yue Wang, Linfeng Song, Dian Yu, Zhenwen Liang, Wenxuan Wang, Zhuosheng Zhang, Rui Wang, Zhaopeng Tu, Haitao Mi, Dong Yu

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

Comments WIP

Can LLMs $\textit{understand}$ Math? -- Exploring the Pitfalls in Mathematical Reasoning

Tiasa Singha Roy, Aditeya Baral, Ayush Rajesh Jhaveri, Yusuf Baig

机构 * New York University（纽约大学） 纠错

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

MathCoder-VL: Bridging Vision and Code for Enhanced Multimodal Mathematical Reasoning

Ke Wang, Junting Pan, Linda Wei, Aojun Zhou, Weikang Shi, Zimu Lu, Han Xiao, Yunqiao Yang, Houxing Ren, Mingjie Zhan, Hongsheng Li

机构 * Multimedia Laboratory (MMLab)（多媒体实验室） ； The Chinese University of Hong Kong（香港中文大学） ； CPII under InnoHK（创新香港科技署CPII） 纠错

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

Comments Accepted to ACL 2025 Findings

From Calculation to Adjudication: Examining LLM judges on Mathematical Reasoning Tasks

Andreas Stephan, Dawei Zhu, Matthias Aßenmacher, Xiaoyu Shen, Benjamin Roth

机构 * Faculty of Computer Science（计算机科学系） ； UniVie Doctoral School Computer Science（维也纳大学计算机科学博士学院） ； Faculty of Philological and Cultural Studies（文学与文化研究系） ； University of Vienna（维也纳大学） ； Saarland University（萨尔兰大学） ； Eastern Institute of Technology（东部技术研究所） ； Department of Statistics（统计系） ； LMU Munich（慕尼黑莱茵河大学） ； Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心） 纠错

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

Unraveling Arithmetic in Large Language Models: The Role of Algebraic Structures

Fu-Chieh Chang, You-Chen Lin, Pei-Yuan Wu

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

Journal ref ICLR 2025 Workshop on Reasoning and Planning for Large Language Models

Holistic Capability Preservation: Towards Compact Yet Comprehensive Reasoning Models

Ling Team, Caizhi Tang, Chilin Fu, Chunwei Wu, Jia Guo, Jianwen Wang, Jingyu Hu, Liang Jiang, Meng Li, Peng Jiao, Pingping Liu, Shaomian Zheng, Shiwei Liang, Shuaicheng Li, Yalin Zhang, Yingting Wu, Yongkang Liu, Zhenyu Huang

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

Comments Based on the further discussion of the working group, the current version is deemed unsuitable for release. We are currently undertaking further work that is expected to involve significant revisions, but this process will require some additional time. We plan to proceed with the release once these updates have been fully implemented

Reasoning on Multiple Needles In A Haystack

Yidong Wang

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

Advancing Mathematical Reasoning in Language Models: The Impact of Problem-Solving Data, Data Synthesis Methods, and Training Stages

Zui Chen, Tianqiao Liu, Mi Tian, Qing Tong, Weiqi Luo, Zitao Liu

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

Comments ICLR 2025

Concise and Organized Perception Facilitates Reasoning in Large Language Models

Junjie Liu, Shaotian Yan, Chen Shen, Zhengdong Xiao, Liang Xie, Wenxiao Wang, Jieping Ye

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

Comments Accepted by NAACL2025 Findings

Procedural Knowledge in Pretraining Drives Reasoning in Large Language Models

Laura Ruis, Maximilian Mozes, Juhan Bae, Siddhartha Rao Kamalakara, Dwarak Talupuru, Acyr Locatelli, Robert Kirk, Tim Rocktäschel, Edward Grefenstette, Max Bartolo

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

Comments Published at ICLR 2025

Med-RLVR: Emerging Medical Reasoning from a 3B base model via reinforcement Learning

Sheng Zhang, Qianchu Liu, Guanghui Qin, Tristan Naumann, Hoifung Poon

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

DynaMath: A Dynamic Visual Benchmark for Evaluating Mathematical Reasoning Robustness of Vision Language Models

Chengke Zou, Xingang Guo, Rui Yang, Junyu Zhang, Bin Hu, Huan Zhang

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

Comments Accepted by ICLR 2025

SIFT: Grounding LLM Reasoning in Contexts via Stickers

Zihao Zeng, Xuyao Huang, Boxiu Li, Zhijie Deng

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

Navigating Semantic Relations: Challenges for Language Models in Abstract Common-Sense Reasoning

Cole Gawin, Yidan Sun, Mayank Kejriwal

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

Comments 5 pages, 3 figures, ACM Web Conference 2025

GSM-Infinite: How Do Your LLMs Behave over Infinitely Increasing Context Length and Reasoning Complexity?

Yang Zhou, Hongyi Liu, Zhuoming Chen, Yuandong Tian, Beidi Chen

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

CARL-GT: Evaluating Causal Reasoning Capabilities of Large Language Models

Ruibo Tu, Hedvig Kjellström, Gustav Eje Henter, Cheng Zhang

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

What Makes In-context Learning Effective for Mathematical Reasoning: A Theoretical Analysis

Jiayu Liu, Zhenya Huang, Chaokun Wang, Xunpeng Huang, Chengxiang Zhai, Enhong Chen

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

SmolTulu: Higher Learning Rate to Batch Size Ratios Can Lead to Better Reasoning in SLMs

Sultan Alrashed

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

Comments 10 pages, 4 figures, and 13 tables. For the SmolTulu-1.7b-instruct model, see: https://huggingface.co/SultanR/SmolTulu-1.7b-Instruct

Towards Learning to Reason: Comparing LLMs with Neuro-Symbolic on Arithmetic Relations in Abstract Reasoning

Michael Hersche, Giacomo Camposampiero, Roger Wattenhofer, Abu Sebastian, Abbas Rahimi

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