大模型推理能力

ALICE: An Interpretable Neural Architecture for Generalization in Substitution Ciphers

Jeff Shen, Lindsay M. Smith

机构 * Princeton University（普林斯顿大学） 纠错

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

Comments Preprint. Project page at https://jshen.net/alice. Added section on probing

Attention Sinks: A 'Catch, Tag, Release' Mechanism for Embeddings

Stephen Zhang, Mustafa Khan, Vardan Papyan

机构 * University of Toronto（多伦多大学） ； Vector Institute（向量研究所） 纠错

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

LongCat-Flash Technical Report

Meituan LongCat Team, Bayan, Bei Li, Bingye Lei, Bo Wang, Bolin Rong, Chao Wang, Chao Zhang, Chen Gao, Chen Zhang, Cheng Sun, Chengcheng Han, Chenguang Xi, Chi Zhang, Chong Peng, Chuan Qin, Chuyu Zhang, Cong Chen, Congkui Wang, Dan Ma, Daoru Pan, Defei Bu, Dengchang Zhao, Deyang Kong, Dishan Liu, Feiye Huo, Fengcun Li, Fubao Zhang, Gan Dong, Gang Liu, Gang Xu, Ge Li, Guoqiang Tan, Guoyuan Lin, Haihang Jing, Haomin Fu, Haonan Yan, Haoxing Wen, Haozhe Zhao, Hong Liu, Hongmei Shi, Hongyan Hao, Hongyin Tang, Huantian Lv, Hui Su, Jiacheng Li, Jiahao Liu, Jiahuan Li, Jiajun Yang, Jiaming Wang, Jian Yang, Jianchao Tan, Jiaqi Sun, Jiaqi Zhang, Jiawei Fu, Jiawei Yang, Jiaxi Hu, Jiayu Qin, Jingang Wang, Jiyuan He, Jun Kuang, Junhui Mei, Kai Liang, Ke He, Kefeng Zhang, Keheng Wang, Keqing He, Liang Gao, Liang Shi, Lianhui Ma, Lin Qiu, Lingbin Kong, Lingtong Si, Linkun Lyu, Linsen Guo, Liqi Yang, Lizhi Yan, Mai Xia, Man Gao, Manyuan Zhang, Meng Zhou, Mengxia Shen, Mingxiang Tuo, Mingyang Zhu, Peiguang Li, Peng Pei, Peng Zhao, Pengcheng Jia, Pingwei Sun, Qi Gu, Qianyun Li, Qingyuan Li, Qiong Huang, Qiyuan Duan, Ran Meng, Rongxiang Weng, Ruichen Shao, Rumei Li, Shizhe Wu, Shuai Liang, Shuo Wang, Suogui Dang, Tao Fang, Tao Li, Tefeng Chen, Tianhao Bai, Tianhao Zhou, Tingwen Xie, Wei He, Wei Huang, Wei Liu, Wei Shi, Wei Wang, Wei Wu, Weikang Zhao, Wen Zan, Wenjie Shi, Xi Nan, Xi Su, Xiang Li, Xiang Mei, Xiangyang Ji, Xiangyu Xi, Xiangzhou Huang, Xianpeng Li, Xiao Fu, Xiao Liu, Xiao Wei, Xiaodong Cai, Xiaolong Chen, Xiaoqing Liu, Xiaotong Li, Xiaowei Shi, Xiaoyu Li, Xili Wang, Xin Chen, Xing Hu, Xingyu Miao, Xinyan He, Xuemiao Zhang, Xueyuan Hao, Xuezhi Cao, Xunliang Cai, Xurui Yang, Yan Feng, Yang Bai, Yang Chen, Yang Yang, Yaqi Huo, Yerui Sun, Yifan Lu, Yifan Zhang, Yipeng Zang, Yitao Zhai, Yiyang Li, Yongjing Yin, Yongkang Lv, Yongwei Zhou, Yu Yang, Yuchen Xie, Yueqing Sun, Yuewen Zheng, Yuhuai Wei, Yulei Qian, Yunfan Liang, Yunfang Tai, Yunke Zhao, Zeyang Yu, Zhao Zhang, Zhaohua Yang, Zhenchao Zhang, Zhikang Xia, Zhiye Zou, Zhizhao Zeng, Zhongda Su, Zhuofan Chen, Zijian Zhang, Ziwen Wang, Zixu Jiang, Zizhe Zhao, Zongyu Wang, Zunhai Su

机构 * Meituan LongCat Team（美团LongCat团队） 纠错

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

NL in the Middle: Code Translation with LLMs and Intermediate Representations

Chi-en Amy Tai, Pengyu Nie, Lukasz Golab, Alexander Wong

专题命中 其他推理 ：chain-of-thought(abstract)；CoT(abstract)

EasyEdit2: An Easy-to-use Steering Framework for Editing Large Language Models

Ziwen Xu, Shuxun Wang, Kewei Xu, Haoming Xu, Mengru Wang, Xinle Deng, Yunzhi Yao, Guozhou Zheng, Huajun Chen, Ningyu Zhang

机构 * Zhejiang University（浙江大学） ； Ocean Research Center of Zhoushan, Zhejiang University（舟山海洋研究中心，浙江大学） 纠错

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

Comments EMNLP 2025 System Demonstrations. Demo: https://www.youtube.com/watch?v=AkfoiPfp5rQ; code: https://github.com/zjunlp/EasyEdit

CDE: Curiosity-Driven Exploration for Efficient Reinforcement Learning in Large Language Models

Runpeng Dai, Linfeng Song, Haolin Liu, Zhenwen Liang, Dian Yu, Haitao Mi, Zhaopeng Tu, Rui Liu, Tong Zheng, Hongtu Zhu, Dong Yu

机构 * Tencent AI Lab（腾讯AI实验室） ； Tencent Multimodal Department（腾讯多模态部门） ； University of North Carolina at Chapel Hill（北卡罗来纳大学夏洛特分校） ； University of Virginia（弗吉尼亚大学） ； University of Maryland, College Park（马里兰大学学院公园分校） 纠错

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

Comments 21 pages

OPRA-Vis: Visual Analytics System to Assist Organization-Public Relationship Assessment with Large Language Models

Sangbong Yoo, Seongbum Seo, Chanyoung Yoon, Hyelim Lee, Jeong-Nam Kim, Chansoo Kim, Yun Jang, Takanori Fujiwara

专题命中 其他推理 ：reasoning(abstract)；chain-of-thought(abstract)

Simple Yet Effective: An Information-Theoretic Approach to Multi-LLM Uncertainty Quantification

Maya Kruse, Majid Afshar, Saksham Khatwani, Anoop Mayampurath, Guanhua Chen, Yanjun Gao

机构 * University of Colorado Anschutz Medical Campus（科罗拉多大学安舒茨医疗校园） ； University of Colorado Boulder（科罗拉多大学博尔德分校） ； University of Wisconsin Madison（威斯康星大学麦迪逊分校） 纠错

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

Comments Accepted to EMNLP 2025 Main Conference

Recall-Extend Dynamics: Enhancing Small Language Models through Controlled Exploration and Refined Offline Integration

Zhong Guan, Likang Wu, Hongke Zhao, Jiahui Wang, Le Wu

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

Grouped Sequency-arranged Rotation: Optimizing Rotation Transformation for Quantization for Free

Euntae Choi, Sumin Song, Woosang Lim, Sungjoo Yoo

机构 * Seoul National University（首尔国立大学） 纠错

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

Comments 7 pages

$\text{M}^{2}$LLM: Multi-view Molecular Representation Learning with Large Language Models

Jiaxin Ju, Yizhen Zheng, Huan Yee Koh, Can Wang, Shirui Pan

机构 * School of Information and Communication Technology, Griffith University（格里菲斯大学信息与通信技术学院） ； Department of Data Science and AI, Monash University（莫纳什大学数据科学与人工智能系） ； Drug Discovery Biology, Monash Institute of Pharmaceutical Sciences, Monash University（莫纳什大学药学科学研究所药物发现生物学部） 纠错

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

Comments IJCAI 2025

HERGC: Heterogeneous Experts Representation and Generative Completion for Multimodal Knowledge Graphs

Yongkang Xiao, Rui Zhang

机构 * University of Minnesota（明尼苏达大学） 纠错

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

Contextually Entangled Gradient Mapping for Optimized LLM Comprehension

Colin Sisate, Alistair Goldfinch, Vincent Waterstone, Sebastian Kingsley, Mariana Blackthorn

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

Comments arXiv admin note: This paper has been withdrawn by arXiv due to disputed and unverifiable authorship

Teaching LLMs How to Learn with Contextual Fine-Tuning

Younwoo Choi, Muhammad Adil Asif, Ziwen Han, John Willes, Rahul G. Krishnan

机构 * University of Toronto（多伦多大学） ； Vector Institute（向量研究所） 纠错

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

Comments ICLR 2025

Understanding Large Language Model Behaviors through Interactive Counterfactual Generation and Analysis

Furui Cheng, Vilém Zouhar, Robin Shing Moon Chan, Daniel Fürst, Hendrik Strobelt, Mennatallah El-Assady

机构 * ETH Zürich（苏黎世联邦理工学院） ； University of Konstanz（康斯坦茨大学） ； IBM Research（IBM研究院） 纠错

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

Small sample-based adaptive text classification through iterative and contrastive description refinement

Amrit Rajeev, Udayaadithya Avadhanam, Harshula Tulapurkar, SaiBarath Sundar

机构 * Mphasis Limited（Mphasis公司） 纠错

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

ETrace:Event-Driven Vulnerability Detection in Smart Contracts via LLM-Based Trace Analysis

Chenyang Peng, Haijun Wang, Yin Wu, Hao Wu, Ming Fan, Yitao Zhao, Ting Liu

专题命中 其他推理 ：reasoning(abstract)；chain-of-thought(abstract)

Comments 4 pages, 1 figure. To appear in Proceedings of the 16th Asia-Pacific Symposium on Internetware (Internetware 2025), ACM ICPS. DOI: https://doi.org/10.1145/3755881.3755934

SmoothRot: Combining Channel-Wise Scaling and Rotation for Quantization-Friendly LLMs

Patrik Czakó, Gábor Kertész, Sándor Szénási

机构 * Doctoral School of Applied Informatics and Applied Mathematics, Obuda University（应用信息学与应用数学博士学院，奥布达大学） ； John von Neumann Faculty of Informatics, Obuda University（约翰·冯·诺依曼信息学院，奥布达大学） 纠错

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

Comments 6 pages, 3 figures, 5 tables. Accepted to IEEE SMC 2025 conference proceedings

Frontier AI Risk Management Framework in Practice: A Risk Analysis Technical Report

Shanghai AI Lab, :, Xiaoyang Chen, Yunhao Chen, Zeren Chen, Zhiyun Chen, Hanyun Cui, Yawen Duan, Jiaxuan Guo, Qi Guo, Xuhao Hu, Hong Huang, Lige Huang, Chunxiao Li, Juncheng Li, Qihao Lin, Dongrui Liu, Xinmin Liu, Zicheng Liu, Chaochao Lu, Xiaoya Lu, Jingjing Qu, Qibing Ren, Jing Shao, Jingwei Shi, Jingwei Sun, Peng Wang, Weibing Wang, Jia Xu, Lewen Yan, Xiao Yu, Yi Yu, Boxuan Zhang, Jie Zhang, Weichen Zhang, Zhijie Zheng, Tianyi Zhou, Bowen Zhou

机构 * Shanghai Artificial Intelligence Laboratory（上海人工智能实验室） 纠错

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

Comments 97 pages, 37 figures

Scalpel vs. Hammer: GRPO Amplifies Existing Capabilities, SFT Replaces Them

Neel Rajani, Aryo Pradipta Gema, Seraphina Goldfarb-Tarrant, Ivan Titov

机构 * Institute for Language, Cognition and Computation (ILCC), University of Edinburgh, United Kingdom（语言、认知与计算研究所（ILCC），爱丁堡大学，英国） ； Institute for Logic, Language and Computation (ILLC), University of Amsterdam, Netherlands（逻辑、语言与计算研究所（ILLC），阿姆斯特丹大学，荷兰） 纠错

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

Journal ref Actionable Interpretability Workshop ICML 2025

Scaling Attention to Very Long Sequences in Linear Time with Wavelet-Enhanced Random Spectral Attention (WERSA)

Vincenzo Dentamaro

机构 * Department of Computer Science University of Bari Aldo Moro（计算机科学系巴里大学Aldo Moro） 纠错

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

Comments 10 pages, 1 figure

Testing Refactoring Engine via Historical Bug Report driven LLM

Haibo Wang, Zhuolin Xu, Shin Hwei Tan

专题命中 其他推理 ：chain-of-thought(abstract)；CoT(abstract)

Comments Accepted at the 2nd ACM international conference on AI Foundation Models and Software Engineering (FORGE 2025)

Beyond Independent Passages: Adaptive Passage Combination Retrieval for Retrieval Augmented Open-Domain Question Answering

Ting-Wen Ko, Jyun-Yu Jiang, Pu-Jen Cheng

机构 * National Taiwan University（国立台湾大学） ； Amazon Search（亚马逊搜索） ； University College London（伦敦大学学院） 纠错

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

SynapseRoute: An Auto-Route Switching Framework on Dual-State Large Language Model

Wencheng Zhang, Shiqin Qiao, Lingjie Luo, Yinfeng Li, Chuanyang Zheng, Qian Xu, Meng Li, Yong Gui, Yijun He, Jianing Qiu, Jindong Hong, Jiankai Sun

机构 * Bytedance（字节跳动） ； Xidian University（西安电子科技大学） ； The Chinese University of Hong Kong（香港中文大学） ； Peking University（北京大学） 纠错

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

Enough Coin Flips Can Make LLMs Act Bayesian

Ritwik Gupta, Rodolfo Corona, Jiaxin Ge, Eric Wang, Dan Klein, Trevor Darrell, David M. Chan

机构 * University of California, Berkeley（加州大学伯克利分校） 纠错

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

Comments ACL 2025 Main

Multimodal Medical Code Tokenizer

Xiaorui Su, Shvat Messica, Yepeng Huang, Ruth Johnson, Lukas Fesser, Shanghua Gao, Faryad Sahneh, Marinka Zitnik

机构 * Department of Biomedical Informatics, Harvard Medical School, Boston, MA, USA（生物医学信息学系，哈佛医学院，波士顿，马萨诸塞州，美国） 纠错

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

Comments ICML'25

The Limited Impact of Medical Adaptation of Large Language and Vision-Language Models

Daniel P. Jeong, Pranav Mani, Saurabh Garg, Zachary C. Lipton, Michael Oberst

机构 * Carnegie Mellon University（卡内基梅隆大学） ； Abridge ； Mistral AI ； Johns Hopkins University（约翰霍普金斯大学） 纠错

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

Comments Extended version of EMNLP 2024 paper arXiv:2411.04118. Includes additional results on clinical note QA tasks and supervised fine-tuning evaluations

Assembly of Experts: Linear-time construction of the Chimera LLM variants with emergent and adaptable behaviors

Henrik Klagges, Robert Dahlke, Fabian Klemm, Benjamin Merkel, Daniel Klingmann, David A. Reiss, Dan Zecha

机构 * TNG Technology Consulting GmbH（TNG技术咨询公司） 纠错

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

Improving LoRA with Variational Learning

Bai Cong, Nico Daheim, Yuesong Shen, Rio Yokota, Mohammad Emtiyaz Khan, Thomas Möllenhoff

机构 * Institute of Science Tokyo（东京科学研究院） ； RIKEN Center for AI Project（RIKEN人工智能项目研究中心） ； Ubiquitous Knowledge Processing Lab (UKP Lab), Department of Computer Science, Technical University of Darmstadt（通用知识处理实验室（UKP实验室），计算机科学系，达姆施塔特技术大学） ； National Research Center for Applied Cybersecurity ATHENE, Germany（应用网络安全国家研究中心ATHENE，德国） ； Huawei Hong Kong Research Center（华为香港研究中心） 纠错

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

Comments 16 pages, 4 figures

Improving Large Language Models with Concept-Aware Fine-Tuning

Michael K. Chen, Xikun Zhang, Jiaxing Huang, Dacheng Tao

机构 * Nanyang Technological University（南洋理工大学） 纠错

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