语言大模型 / LLM

Extracting Events Like Code: A Multi-Agent Programming Framework for Zero-Shot Event Extraction

Quanjiang Guo, Sijie Wang, Jinchuan Zhang, Ben Zhang, Zhao Kang, Ling Tian, Ke Yan

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

Comments 11 pages, 5 figures, accepted by AAAI 2026 (Oral)

GEM: Generative Entropy-Guided Preference Modeling for Few-shot Alignment of LLMs

Yiyang Zhao, Huiyu Bai, Xuejiao Zhao

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

Comments This paper has been accepted by AAAI 2026-AIA and designated as an oral presentation paper

Comprehension Without Competence: Architectural Limits of LLMs in Symbolic Computation and Reasoning

Zheng Zhang

机构 * Amazon Web Services（亚马逊网络服务） 纠错

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

Comments v2: Two TMLR revision rounds addressing reviewer feedback. Added real-world validation (3.4), interpretability analysis (7), computational hallucination framework, strengthened theory. v3: Sec 3.2 - added transformer architecture diagram, clarified UAT capacity vs computational limits, improved role specialization theorem presentation

Debiasing LLMs by Masking Unfairness-Driving Attention Heads

Tingxu Han, Wei Song, Ziqi Ding, Ziming Li, Chunrong Fang, Yuekang Li, Dongfang Liu, Zhenyu Chen, Zhenting Wang

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

GAP: Graph-Based Agent Planning with Parallel Tool Use and Reinforcement Learning

Jiaqi Wu, Qinlao Zhao, Zefeng Chen, Kai Qin, Yifei Zhao, Xueqian Wang, Yuhang Yao

机构 * Tsinghua University（清华大学） ； Huazhong University of Science and Technology（华中科技大学） ； National University of Singapore（新加坡国立大学） ； Carnegie Mellon University（卡内基梅隆大学） 纠错

专题命中 推理与问题求解 ：large language model(abstract)；language model(abstract)；foundation model(abstract)；SFT(abstract)

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） 纠错

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

From Large to Small: Transferring CUDA Optimization Expertise via Reasoning Graph

Junfeng Gong, Zhiyi Wei, Junying Chen, Cheng Liu, Huawei Li

机构 * Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所） ； University of Chinese Academy of Sciences（中国科学院大学） ； South China University of Technology（华南理工大学） 纠错

专题命中 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；small language model(abstract)

Test-time Prompt Intervention

Chenxu Yang, Qingyi Si, Mz Dai, Dingyu Yao, Mingyu Zheng, Minghui Chen, Zheng Lin, Weiping Wang

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

Comments 24 pages, 20 figures, under review

Fine-Tuned Thoughts: Leveraging Chain-of-Thought Reasoning for Industrial Asset Health Monitoring

Shuxin Lin, Dhaval Patel, Christodoulos Constantinides

机构 * IBM Research（IBM研究院） 纠错

专题命中 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；small language model(abstract)

Comments Accepted at EMNLP 2025

Reinforcement Learning for Out-of-Distribution Reasoning in LLMs: An Empirical Study on Diagnosis-Related Group Coding

Hanyin Wang, Zhenbang Wu, Gururaj Kolar, Hariprasad Korsapati, Brian Bartlett, Bryan Hull, Jimeng Sun

机构 * School of Computing and Data Science, UIUC（计算与数据科学学院，UIUC） ； Mayo Clinic Health System（梅奥诊所健康系统） ； Mayo Clinic Rochester（梅奥诊所罗切斯特分部） ； Mayo Clinic Phoenix（梅奥诊所凤凰城分部） ； Carle Illinois College of Medicine, UIUC（Carle伊利诺伊医学院，UIUC） 纠错

专题命中 推理与问题求解 ：large language model(abstract)；language model(abstract)；pretraining(abstract)；SFT(abstract)

Reasoning Pattern Matters: Learning to Reason without Human Rationales

Chaoxu Pang, Yixuan Cao, Ping Luo

机构 * Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所智能信息处理重点实验室） 纠错

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

Comments Submitted to Frontiers of Computer Science

Can Speech LLMs Think while Listening?

Yi-Jen Shih, Desh Raj, Chunyang Wu, Wei Zhou, SK Bong, Yashesh Gaur, Jay Mahadeokar, Ozlem Kalinli, Mike Seltzer

机构 * The University of Texas at Austin（德克萨斯大学奥斯汀分校） ； Meta Superintelligence Labs（Meta超智能实验室） 纠错

专题命中 推理与问题求解 ：large language model(abstract)；language model(abstract)；preference optimization(abstract)；prompting(abstract)

Non-Interactive Symbolic-Aided Chain-of-Thought for Logical Reasoning

Phuong Minh Nguyen, Tien Huu Dang, Naoya Inoue

机构 * Japan Advanced Institute of Science and Technology（日本科学技术先进研究院） 纠错

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

Comments Accepted in The 39th Pacific Asia Conference on Language, Information and Computation (PACLIC 39)

One Model, Many Morals: Uncovering Cross-Linguistic Misalignments in Computational Moral Reasoning

Sualeha Farid, Jayden Lin, Zean Chen, Shivani Kumar, David Jurgens

机构 * University of Michigan（密歇根大学） 纠错

专题命中 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；pretraining(abstract)

Comments 22 pages, 11 figures, 6 tables

JUREX-4E: Juridical Expert-Annotated Four-Element Knowledge Base for Legal Reasoning

Huanghai Liu, Quzhe Huang, Qingjing Chen, Yiran Hu, Jiayu Ma, Yun Liu, Weixing Shen, Yansong Feng

机构 * School of Law, Tsinghua University（清华大学法学院） ； Wangxuan Institute of Computer Technology, Peking University（北京大学王璇计算机技术研究所） ； Department of Legal Studies, University of Bologna（博洛尼亚大学法律系） 纠错

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

One Filters All: A Generalist Filter for State Estimation

Shiqi Liu, Wenhan Cao, Chang Liu, Zeyu He, Tianyi Zhang, Shengbo Eben Li

机构 * School of Vehicle and Mobility, Tsinghua University（清华大学车辆与移动系统学院） ； College of Engineering, Peking University（北京大学工程学院） ； College of AI, Tsinghua University（清华大学人工智能学院） 纠错

专题命中 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；foundation model(abstract)

Comments NeurIPS 2025

Can LLMs Explain Themselves Counterfactually?

Zahra Dehghanighobadi, Asja Fischer, Muhammad Bilal Zafar

机构 * Ruhr University Bochum（博尔塔伦大学博赫姆分校） ； UAR Research Center for Trustworthy Data Science and Security（UAR可信数据科学与安全研究中心） 纠错

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

SalaMAnder: Shapley-based Mathematical Expression Attribution and Metric for Chain-of-Thought Reasoning

Yue Xin, Chen Shen, Shaotian Yan, Xiaosong Yuan, Yaoming Wang, Xiaofeng Zhang, Chenxi Huang, Jieping Ye

机构 * Shanghai Jiao Tong University（上海交通大学） ； Alibaba Cloud Computing（阿里云计算） 纠错

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

Comments accpeted by EMNLP 2025

No Need for Explanations: LLMs can implicitly learn from mistakes in-context

Lisa Alazraki, Maximilian Mozes, Jon Ander Campos, Tan Yi-Chern, Marek Rei, Max Bartolo

机构 * Imperial College London（伦敦帝国学院） ； Cohere 纠错

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

Comments EMNLP 2025

Process-Supervised Reinforcement Learning for Interactive Multimodal Tool-Use Agents

Weiting Tan, Xinghua Qu, Ming Tu, Meng Ge, Andy T. Liu, Philipp Koehn, Lu Lu

机构 * Johns Hopkins University（约翰霍普金斯大学） 纠错

专题命中 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；foundation model(abstract)

CANDY: Benchmarking LLMs' Limitations and Assistive Potential in Chinese Misinformation Fact-Checking

Ruiling Guo, Xinwei Yang, Chen Huang, Tong Zhang, Yong Hu

机构 * School of Cyber Science and Engineering, Sichuan University, China（四川大学网络科学与工程学院） ； College of Computer Science, Sichuan University, China（四川大学计算机学院） ； Institute of Data Science, National University of Singapore, Singapore（新加坡国立大学数据科学研究所） 纠错

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

Comments Findings of EMNLP 2025

POT: Inducing Overthinking in LLMs via Black-Box Iterative Optimization

Xinyu Li, Tianjin Huang, Ronghui Mu, Xiaowei Huang, Gaojie Jin

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

MATATA: Weakly Supervised End-to-End MAthematical Tool-Augmented Reasoning for Tabular Applications

Vishnou Vinayagame, Gregory Senay, Luis Martí

机构 * Docugami Inc（Docugami公司） ； University of Toronto（多伦多大学） 纠错

专题命中 推理与问题求解 ：language model(abstract)；small language model(abstract)；SLM(abstract)；language agent(abstract)

Comments Published as a conference paper at ICDAR 2025

Who Sees What? Structured Thought-Action Sequences for Epistemic Reasoning in LLMs

Luca Annese, Sabrina Patania, Silvia Serino, Tom Foulsham, Silvia Rossi, Azzurra Ruggeri, Dimitri Ognibene

机构 * University of Milan-Bicocca（米兰-比科卡大学） ； University of Essex（埃塞克斯大学） ； University of Naples Federico II（那不勒斯费德里科二世大学） ； TUM School of Social Sciences and Technology（技术与社会科学学院） 纠错

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

Comments Accepted at ICSR25

APIO: Automatic Prompt Induction and Optimization for Grammatical Error Correction and Text Simplification

Artem Chernodub, Aman Saini, Yejin Huh, Vivek Kulkarni, Vipul Raheja

机构 * Grammarly 纠错

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

Comments Accepted for publication at Recent Advances in Natural Language Processing conference (RANLP 2025)

TEN: Table Explicitization, Neurosymbolically

Nikita Mehrotra, Aayush Kumar, Sumit Gulwani, Arjun Radhakrishna, Ashish Tiwari

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

Show, Don't Tell: Uncovering Implicit Character Portrayal using LLMs

Brandon Jaipersaud, Zining Zhu, Frank Rudzicz, Elliot Creager

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

Journal ref NeurIPS 2024 Creativity and Generative AI Workshop

R2Vul: Learning to Reason about Software Vulnerabilities with Reinforcement Learning and Structured Reasoning Distillation

Martin Weyssow, Chengran Yang, Junkai Chen, Ratnadira Widyasari, Ting Zhang, Huihui Huang, Huu Hung Nguyen, Yan Naing Tun, Tan Bui, Yikun Li, Ang Han Wei, Frank Liauw, Eng Lieh Ouh, Lwin Khin Shar, David Lo

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

Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning

Bowen Jin, Hansi Zeng, Zhenrui Yue, Jinsung Yoon, Sercan Arik, Dong Wang, Hamed Zamani, Jiawei Han

机构 * Department of Computer Science, University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校计算机科学系） ； Center for Intelligent Information Retrieval, University of Massachusetts Amherst（马萨诸塞大学阿姆赫斯特分校智能信息检索中心） ； Google Cloud AI Research（谷歌云人工智能研究） 纠错

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

Comments 31 pages

Understanding Foundation Models: Are We Back in 1924?

Alan F. Smeaton

机构 * Dublin City University（都柏林城市大学） 纠错

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

Comments 7 pages, 4 Figures, to appear in Proceedings of the 2nd International Conference on Foundation and Large Language Models (FLLM2024) 26-29 November, 2024, Dubai, UAE