大模型推理能力

Feather-SQL: A Lightweight NL2SQL Framework with Dual-Model Collaboration Paradigm for Small Language Models

Wenqi Pei, Hailing Xu, Hengyuan Zhao, Shizheng Hou, Han Chen, Zining Zhang, Pingyi Luo, Bingsheng He

专题命中 其他推理 ：reasoning(abstract)；分类 cs.CL、cs.AI

Comments DL4C @ ICLR 2025

Memory-Augmented Transformers: A Systematic Review from Neuroscience Principles to Enhanced Model Architectures

Parsa Omidi, Xingshuai Huang, Axel Laborieux, Bahareh Nikpour, Tianyu Shi, Armaghan Eshaghi

机构 * Huawei Technologies Canada（华为加拿大技术有限公司） ； Huawei Technologies Switzerland（华为瑞士技术有限公司） 纠错

专题命中 其他推理 ：reasoning(abstract)；分类 cs.CL、cs.LG

Reference Points in LLM Sentiment Analysis: The Role of Structured Context

Junichiro Niimi

机构 * Meijo University（名古屋大学） ； RIKEN（理化学研究所） ； AIP（Advanced Institute for Particle Physics） 纠错

专题命中 其他推理 ：reasoning(abstract)；分类 cs.CL、cs.AI

gpt-oss-120b & gpt-oss-20b Model Card

OpenAI, :, Sandhini Agarwal, Lama Ahmad, Jason Ai, Sam Altman, Andy Applebaum, Edwin Arbus, Rahul K. Arora, Yu Bai, Bowen Baker, Haiming Bao, Boaz Barak, Ally Bennett, Tyler Bertao, Nivedita Brett, Eugene Brevdo, Greg Brockman, Sebastien Bubeck, Che Chang, Kai Chen, Mark Chen, Enoch Cheung, Aidan Clark, Dan Cook, Marat Dukhan, Casey Dvorak, Kevin Fives, Vlad Fomenko, Timur Garipov, Kristian Georgiev, Mia Glaese, Tarun Gogineni, Adam Goucher, Lukas Gross, Katia Gil Guzman, John Hallman, Jackie Hehir, Johannes Heidecke, Alec Helyar, Haitang Hu, Romain Huet, Jacob Huh, Saachi Jain, Zach Johnson, Chris Koch, Irina Kofman, Dominik Kundel, Jason Kwon, Volodymyr Kyrylov, Elaine Ya Le, Guillaume Leclerc, James Park Lennon, Scott Lessans, Mario Lezcano-Casado, Yuanzhi Li, Zhuohan Li, Ji Lin, Jordan Liss, Lily, Liu, Jiancheng Liu, Kevin Lu, Chris Lu, Zoran Martinovic, Lindsay McCallum, Josh McGrath, Scott McKinney, Aidan McLaughlin, Song Mei, Steve Mostovoy, Tong Mu, Gideon Myles, Alexander Neitz, Alex Nichol, Jakub Pachocki, Alex Paino, Dana Palmie, Ashley Pantuliano, Giambattista Parascandolo, Jongsoo Park, Leher Pathak, Carolina Paz, Ludovic Peran, Dmitry Pimenov, Michelle Pokrass, Elizabeth Proehl, Huida Qiu, Gaby Raila, Filippo Raso, Hongyu Ren, Kimmy Richardson, David Robinson, Bob Rotsted, Hadi Salman, Suvansh Sanjeev, Max Schwarzer, D. Sculley, Harshit Sikchi, Kendal Simon, Karan Singhal, Yang Song, Dane Stuckey, Zhiqing Sun, Philippe Tillet, Sam Toizer, Foivos Tsimpourlas, Nikhil Vyas, Eric Wallace, Xin Wang, Miles Wang, Olivia Watkins, Kevin Weil, Amy Wendling, Kevin Whinnery, Cedric Whitney, Hannah Wong, Lin Yang, Yu Yang, Michihiro Yasunaga, Kristen Ying, Wojciech Zaremba, Wenting Zhan, Cyril Zhang, Brian Zhang, Eddie Zhang, Shengjia Zhao

机构 * OpenAI 纠错

专题命中 其他推理 ：reasoning(abstract)；分类 cs.CL、cs.AI

Speed Always Wins: A Survey on Efficient Architectures for Large Language Models

Weigao Sun, Jiaxi Hu, Yucheng Zhou, Jusen Du, Disen Lan, Kexin Wang, Tong Zhu, Xiaoye Qu, Yu Zhang, Xiaoyu Mo, Daizong Liu, Yuxuan Liang, Wenliang Chen, Guoqi Li, Yu Cheng

机构 * Shanghai AI Laboratory（上海人工智能实验室） ； HKUST (GZ)（香港科技大学） ； University of Macau（澳门大学） ； Institute of Automation Chinese Academy of Sciences（中国科学院自动化研究所） ； Soochow University（苏州大学） ； KTH Royal Institute of Technology（皇家理工学院） ； Peking University（北京大学） ； The Chinese University of Hong Kong（香港中文大学） 纠错

专题命中 其他推理 ：reasoning(abstract)；分类 cs.CL、cs.AI

Comments Survey, 82 pages, GitHub: https://github.com/weigao266/Awesome-Efficient-Arch

Evaluating the Role of Large Language Models in Legal Practice in India

Rahul Hemrajani

机构 * National Law School of India（印度国家法律学校） 纠错

专题命中 其他推理 ：reasoning(abstract)；分类 cs.CL、cs.AI

From Model Performance to Claim: How a Change of Focus in Machine Learning Replicability Can Help Bridge the Responsibility Gap

Tianqi Kou

机构 * Penn State University（宾夕法尼亚州立大学） 纠错

专题命中 其他推理 ：reasoning(abstract)；分类 cs.AI、cs.LG

Comments FAccT 2024

Do Biased Models Have Biased Thoughts?

Swati Rajwal, Shivank Garg, Reem Abdel-Salam, Abdelrahman Zayed

机构 * Emory University（埃默里大学） ； Indian Institute of Technology Roorkee（印度理工学院罗里克分校） ； Cairo University（开罗大学） ； Mila - Quebec AI Institute（魁北克人工智能研究所） ； Polytechnique Montréal（蒙特利尔理工学院） ； Amazon（亚马逊） 纠错

专题命中 其他推理 ：chain-of-thought(abstract)；分类 cs.CL、cs.AI

Comments Accepted at main track of the Second Conference on Language Modeling (COLM 2025)

A Few Words Can Distort Graphs: Knowledge Poisoning Attacks on Graph-based Retrieval-Augmented Generation of Large Language Models

Jiayi Wen, Tianxin Chen, Zhirun Zheng, Cheng Huang

专题命中 其他推理 ：reasoning(abstract)；分类 cs.CL、cs.AI

Grasp-HGN: Grasping the Unexpected

Mehrshad Zandigohar, Mallesham Dasari, Gunar Schirner

专题命中 其他推理 ：reasoning(abstract)；分类 cs.AI、cs.LG

Comments Paper accepted at ACM Transactions on Embedded Computing Systems

ARAG: Agentic Retrieval Augmented Generation for Personalized Recommendation

Reza Yousefi Maragheh, Pratheek Vadla, Priyank Gupta, Kai Zhao, Aysenur Inan, Kehui Yao, Jianpeng Xu, Praveen Kanumala, Jason Cho, Sushant Kumar

机构 * Walmart Global Tech（沃尔玛全球科技） 纠错

专题命中 其他推理 ：reasoning(abstract)；分类 cs.CL、cs.AI

Bifrost-1: Bridging Multimodal LLMs and Diffusion Models with Patch-level CLIP Latents

Han Lin, Jaemin Cho, Amir Zadeh, Chuan Li, Mohit Bansal

机构 * UNC Chapel Hill（北卡罗来纳大学教堂山分校） ； Lambda 纠错

专题命中 其他推理 ：reasoning(abstract)；分类 cs.CL、cs.AI

Comments Project Page: https://bifrost-1.github.io

Cooper: Co-Optimizing Policy and Reward Models in Reinforcement Learning for Large Language Models

Haitao Hong, Yuchen Yan, Xingyu Wu, Guiyang Hou, Wenqi Zhang, Weiming Lu, Yongliang Shen, Jun Xiao

机构 * Zhejiang University（浙江大学） 纠错

专题命中 其他推理 ：reasoning(abstract)；分类 cs.CL、cs.AI

Comments Project Page: https://zju-real.github.io/cooper Code: https://github.com/zju-real/cooper

A Multi-Stage Large Language Model Framework for Extracting Suicide-Related Social Determinants of Health

Song Wang, Yishu Wei, Haotian Ma, Max Lovitt, Kelly Deng, Yuan Meng, Zihan Xu, Jingze Zhang, Yunyu Xiao, Ying Ding, Xuhai Xu, Joydeep Ghosh, Yifan Peng

机构 * Cockrell School of Engineering, The University of Texas at Austin（德克萨斯大学奥斯汀分校工程学院） ； Population Health Sciences, Weill Cornell Medicine（韦尔·柯尔医学中心流行病学与卫生科学系） ； School of Information, The University of Texas at Austin（德克萨斯大学奥斯汀分校信息学院） ； Department of Biomedical Informatics, Columbia University（哥伦比亚大学生物医学信息学系） 纠错

专题命中 其他推理 ：reasoning(abstract)；分类 cs.CL、cs.AI

Rationale-guided Prompting for Knowledge-based Visual Question Answering

Zhongjian Hu, Peng Yang, Bing Li, Fengyuan Liu

专题命中 其他推理 ：CoT(abstract)；分类 cs.CL、cs.AI

Comments We would like to withdraw this submission due to ongoing internal review and coordination among the author team. Upon the supervisor's recommendation, we have decided to delay public dissemination until the manuscript undergoes further refinement and aligns with our intended academic trajectory

HarmonyGuard: Toward Safety and Utility in Web Agents via Adaptive Policy Enhancement and Dual-Objective Optimization

Yurun Chen, Xavier Hu, Yuhan Liu, Keting Yin, Juncheng Li, Zhuosheng Zhang, Shengyu Zhang

机构 * Zhejiang University（浙江大学） ； Xiamen University（厦门大学） ； Shanghai Jiao Tong University（上海交通大学） 纠错

专题命中 其他推理 ：reasoning(abstract)；分类 cs.CL、cs.AI

Decomposing the Entropy-Performance Exchange: The Missing Keys to Unlocking Effective Reinforcement Learning

Jia Deng, Jie Chen, Zhipeng Chen, Wayne Xin Zhao, Ji-Rong Wen

专题命中 其他推理 ：reasoning(abstract)；分类 cs.CL、cs.AI

Comments 7 pages, 20 figures

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 其他推理 ：reasoning(abstract)；分类 cs.AI、cs.LG

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

Discrete Tokenization for Multimodal LLMs: A Comprehensive Survey

Jindong Li, Yali Fu, Jiahong Liu, Linxiao Cao, Wei Ji, Menglin Yang, Irwin King, Ming-Hsuan Yang

专题命中 其他推理 ：reasoning(abstract)；分类 cs.CL、cs.AI

Don't Lag, RAG: Training-Free Adversarial Detection Using RAG

Roie Kazoom, Raz Lapid, Moshe Sipper, Ofer Hadar

机构 * Electrical and Computer Engineering, Ben Gurion University, Beer Sheba 84105, Israel（电子与计算机工程系，本· Gurion 大学） ； Computer Science, Ben Gurion University, Beer Sheba 84105, Israel（计算机科学系，本· Gurion 大学） 纠错

专题命中 其他推理 ：reasoning(abstract)；分类 cs.AI、cs.LG

Comments Accepted at VecDB @ ICML 2025

Improving the Performance of Sequential Recommendation Systems with an Extended Large Language Model

Sinnyum Choi, Woong Kim

机构 * Department of AI Convergence Software（人工智能融合软件系） ； Dong-Seoul University（东首尔大学） 纠错

专题命中 其他推理 ：reasoning(abstract)；分类 cs.CL、cs.AI

Accelerating Multimodal Large Language Models via Dynamic Visual-Token Exit and the Empirical Findings

Qiong Wu, Wenhao Lin, Yiyi Zhou, Weihao Ye, Zhanpeng Zen, Xiaoshuai Sun, Rongrong Ji

机构 * Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University（中国教育部多媒体可信感知与高效计算重点实验室，厦门大学） ； Institute of Artificial Intelligence, Xiamen University（厦门大学人工智能研究院） 纠错

专题命中 其他推理 ：reasoning(abstract)；分类 cs.CL、cs.LG

The Moral Gap of Large Language Models

Maciej Skorski, Alina Landowska

专题命中 其他推理 ：reasoning(abstract)；分类 cs.CL、cs.LG

Comments preprint

AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning

Yi Zhang, An Zhang, XiuYu Zhang, Leheng Sheng, Yuxin Chen, Zhenkai Liang, Xiang Wang

专题命中 其他推理 ：reasoning(abstract)；分类 cs.AI、cs.LG

CCL-XCoT: An Efficient Cross-Lingual Knowledge Transfer Method for Mitigating Hallucination Generation

Weihua Zheng, Roy Ka-Wei Lee, Zhengyuan Liu, Kui Wu, AiTi Aw, Bowei Zou

机构 * Institute for Infocomm Research (I 2 R), A*STAR, Singapore（信息与通信研究机构（I2R），A*STAR，新加坡） 纠错

专题命中 其他推理 ：chain-of-thought(abstract)；分类 cs.CL、cs.AI

Prompt engineering paradigms for medical applications: scoping review and recommendations for better practices

Jamil Zaghir, Marco Naguib, Mina Bjelogrlic, Aurélie Névéol, Xavier Tannier, Christian Lovis

专题命中 其他推理 ：chain-of-thought(abstract)；分类 cs.CL、cs.LG

Journal ref Journal of Medical Internet Research, 26, e60501 (2024)

Large Language Models in Cybersecurity: Applications, Vulnerabilities, and Defense Techniques

Niveen O. Jaffal, Mohammed Alkhanafseh, David Mohaisen

机构 * Birzeit University（巴伊兹大学） ； University of Central Florida（中央佛罗里达大学） 纠错

专题命中 其他推理 ：reasoning(abstract)；分类 cs.AI、cs.LG

Comments 21 pages

Referential ambiguity and clarification requests: comparing human and LLM behaviour

Chris Madge, Matthew Purver, Massimo Poesio

机构 * Queen Mary University of London（伦敦大学Queen Mary） 纠错

专题命中 其他推理 ：reasoning(abstract)；分类 cs.CL、cs.AI

Automating SPARQL Query Translations between DBpedia and Wikidata

Malte Christian Bartels, Debayan Banerjee, Ricardo Usbeck

机构 * Leuphana University of Lüneburg（吕贝克大学） 纠错

专题命中 其他推理 ：chain-of-thought(abstract)；分类 cs.CL、cs.AI

Comments 18 pages, 2 figues. Paper accepted at SEMANTiCS 2025 conference happening on September 2025

Tiny Reward Models

Sarah Pan

机构 * Massachusetts Institute of Technology（麻省理工学院） 纠错

专题命中 其他推理 ：reasoning(abstract)；分类 cs.CL、cs.AI

Comments 2025 ICML Efficient Systems for Foundation Models Workshop