语言大模型 / LLM

P2P: A Poison-to-Poison Remedy for Reliable Backdoor Defense in LLMs

Shuai Zhao, Xinyi Wu, Shiqian Zhao, Xiaobao Wu, Zhongliang Guo, Yanhao Jia, Anh Tuan Luu

机构 * Nanyang Technological University, Singapore（南洋理工大学） ； Shanghai Jiao Tong University, Shanghai, China（上海交通大学） 纠错

专题命中 指令微调 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

LLMs Show Surface-Form Brittleness Under Paraphrase Stress Tests

Juan Miguel Navarro Carranza

机构 * Stanford University（斯坦福大学） 纠错

专题命中 指令微调 ：large language model(abstract)；language model(abstract)；分类 cs.CL；LLM(comments)

Comments NeurIPS 2025 Workshop. Evaluating the Evolving LLM Lifecycle: Benchmarks, Emergent Abilities, and Scaling. Selected for contributed talk

Adaptive LoRA Experts Allocation and Selection for Federated Fine-Tuning

Lei Wang, Jieming Bian, Letian Zhang, Jie Xu

机构 * University of Florida（佛罗里达大学） ； Middle Tennessee State University（中田纳西州立大学） 纠错

专题命中 指令微调 ：large language model(abstract)；language model(abstract)；分类 cs.LG

Comments Accepted to NeurIPS 2025

Untangling Component Imbalance in Hybrid Linear Attention Conversion Methods

Martin Benfeghoul, Teresa Delgado, Adnan Oomerjee, Haitham Bou Ammar, Jun Wang, Zafeirios Fountas

机构 * Huawei, Noah’s Ark Lab（华为、诺亚实验室） ； AI Centre, Department of Computer Science, University College London（人工智能中心、计算机科学系、伦敦大学学院） 纠错

专题命中 指令微调 ：post-training(abstract)；分类 cs.CL、cs.AI、cs.LG

Robo-Instruct: Simulator-Augmented Instruction Alignment For Finetuning Code LLMs

Zichao Hu, Junyi Jessy Li, Arjun Guha, Joydeep Biswas

专题命中 指令微调 ：LLM(abstract)；分类 cs.CL、cs.AI；language model(comments)

Comments Conference on Language Modeling (COLM) 2025, Project site: https://amrl.cs.utexas.edu/robo-instruct/

Site-Level Fine-Tuning with Progressive Layer Freezing: Towards Robust Prediction of Bronchopulmonary Dysplasia from Day-1 Chest Radiographs in Extremely Preterm Infants

Sybelle Goedicke-Fritz, Michelle Bous, Annika Engel, Matthias Flotho, Pascal Hirsch, Hannah Wittig, Dino Milanovic, Dominik Mohr, Mathias Kaspar, Sogand Nemat, Dorothea Kerner, Arno Bücker, Andreas Keller, Sascha Meyer, Michael Zemlin, Philipp Flotho

专题命中 指令微调 ：pretraining(abstract)；分类 cs.AI、cs.LG

Comments S.G.-F., M.B., and A.E. contributed equally to this work and share first authorship. M.Z. and P.F. contributed equally to this work and share senior authorship

MEC$^3$O: Multi-Expert Consensus for Code Time Complexity Prediction

Joonghyuk Hahn, Soohan Lim, Yo-Sub Han

机构 * Department of Computer Science, Yonsei University（延世大学计算机科学系） 纠错

专题命中 指令微调 ：LLM(abstract)；分类 cs.AI

Comments 24 pages, 11 figures, 10 tables

RePIC: Reinforced Post-Training for Personalizing Multi-Modal Language Models

Yeongtak Oh, Dohyun Chung, Juhyeon Shin, Sangha Park, Johan Barthelemy, Jisoo Mok, Sungroh Yoon

专题命中 后训练与偏好优化 ：language model(title,abstract)；post-training(title,abstract)；large language model(abstract)；SFT(abstract)

Comments Accepted to NeurIPS 2025

Logits Replay + MoClip: Stabilized, Low-Cost Post-Training with Minimal Forgetting

Suming Qiu, Jing Li, Zhicheng Zhou, Junjie Huang, Linyuan Qiu, Zhijie Sun

机构 * Global Technical Service (GTS) Huawei Technologies Co., Ltd（华为技术有限公司全球技术服务部） 纠错

专题命中 后训练与偏好优化 ：post-training(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.LG

RPO: Retrieval Preference Optimization for Robust Retrieval-Augmented Generation

Shi-Qi Yan, Quan Liu, Zhen-Hua Ling

机构 * National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China（语音与语言信息处理国家工程研究中心，中国科学技术大学） ； State Key Laboratory of Cognitive Intelligence, iFLYTEK Research（认知智能国家重点实验室，iFLYTEK研究院） 纠错

专题命中 后训练与偏好优化 ：preference optimization(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL

DenseDPO: Fine-Grained Temporal Preference Optimization for Video Diffusion Models

Ziyi Wu, Anil Kag, Ivan Skorokhodov, Willi Menapace, Ashkan Mirzaei, Igor Gilitschenski, Sergey Tulyakov, Aliaksandr Siarohin

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

专题命中 后训练与偏好优化 ：preference optimization(title,abstract)；language model(abstract)；post-training(abstract)

Comments NeurIPS 2025 Spotlight. Project page: https://snap-research.github.io/DenseDPO/

EVALUESTEER: Measuring Reward Model Steerability Towards Values and Preferences

Kshitish Ghate, Andy Liu, Devansh Jain, Taylor Sorensen, Atoosa Kasirzadeh, Aylin Caliskan, Mona T. Diab, Maarten Sap

机构 * University of Washington（华盛顿大学） ； Carnegie Mellon University（卡内基梅隆大学） 纠错

专题命中 后训练与偏好优化 ：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

Comments Preprint under review

VAGPO: Vision-augmented Asymmetric Group Preference Optimization for Graph Routing Problems

Shiyan Liu, Bohan Tan, Zhiguang Cao, Yan Jin

机构 * Huazhong University of Science and Technology（华中科技大学） ； Singapore Management University（新加坡管理学院） 纠错

专题命中 后训练与偏好优化 ：preference optimization(title,abstract)；分类 cs.AI、cs.LG

Lesion-Aware Post-Training of Latent Diffusion Models for Synthesizing Diffusion MRI from CT Perfusion

Junhyeok Lee, Hyunwoong Kim, Hyungjin Chung, Heeseong Eom, Joon Jang, Chul-Ho Sohn, Kyu Sung Choi

机构 * College of Medicine, Seoul National University, Seoul, Republic of Korea（首尔国立大学医学院） ； Department of Radiology, Seoul National University Hospital（首尔国立大学医院放射科） ； Department of Biomedical Sciences, Seoul National University（首尔国立大学生物医学科学系） 纠错

专题命中 后训练与偏好优化 ：post-training(title,abstract)

Comments MICCAI 2025, Lecture Notes in Computer Science Vol. 15961

Journal ref Med Image Comput Comput Assist Interv. LNCS 15961, 282-291, Springer, 2026

Online Rubrics Elicitation from Pairwise Comparisons

MohammadHossein Rezaei, Robert Vacareanu, Zihao Wang, Clinton Wang, Bing Liu, Yunzhong He, Afra Feyza Akyürek

专题命中 后训练与偏好优化 ：LLM(abstract)；post-training(abstract)；分类 cs.CL、cs.AI、cs.LG

Don't Waste Mistakes: Leveraging Negative RL-Groups via Confidence Reweighting

Yunzhen Feng, Parag Jain, Anthony Hartshorn, Yaqi Duan, Julia Kempe

机构 * Meta Superintelligence Labs（Meta超智能实验室） ； New York University（纽约大学） 纠错

专题命中 后训练与偏好优化 ：large language model(abstract)；language model(abstract)；分类 cs.LG

Issue Localization via LLM-Driven Iterative Code Graph Searching

Zhonghao Jiang, Xiaoxue Ren, Meng Yan, Wei Jiang, Yong Li, Zhongxin Liu

机构 * The State Key Laboratory of Blockchain and Data Security, Zhejiang University, Hangzhou, China（区块链与数据安全国家重点实验室，浙江大学，杭州，中国） ； School of Big Data and Software Engineering, Chongqing University, Chongqing, China（大数据与软件工程学院，重庆大学，重庆，中国） 纠错

专题命中 长上下文与记忆 ：LLM(title,abstract)；分类 cs.CL、cs.AI

Comments Accepted by ASE 2025

Haystack Engineering: Context Engineering for Heterogeneous and Agentic Long-Context Evaluation

Mufei Li, Dongqi Fu, Limei Wang, Si Zhang, Hanqing Zeng, Kaan Sancak, Ruizhong Qiu, Haoyu Wang, Xiaoxin He, Xavier Bresson, Yinglong Xia, Chonglin Sun, Pan Li

机构 * Georgia Institute of Technology（佐治亚理工学院） ； Meta AI ； University of Illinois Urbana–Champaign（伊利诺伊大学厄巴纳-香槟分校） ； National University of Singapore（新加坡国立大学） 纠错

专题命中 长上下文与记忆 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

Comments Code available at https://github.com/Graph-COM/HaystackCraft

Understanding and Improving Information Preservation in Prompt Compression for LLMs

Weronika Łajewska, Momchil Hardalov, Laura Aina, Neha Anna John, Hang Su, Lluís Màrquez

机构 * University of Stavanger（斯塔万格大学） ； AWS AI Labs（AWS AI实验室） ； Technical University of Catalonia (UPC)（加泰罗尼亚理工大学） 纠错

专题命中 长上下文与记忆 ：large language model(abstract)；language model(abstract)；prompting(abstract)；分类 cs.CL、cs.LG

Comments Accepted to EMNLP 2025 (Findings), 22 pages, 6 figures, 24 tables

Agentic-KGR: Co-evolutionary Knowledge Graph Construction through Multi-Agent Reinforcement Learning

Jing Li, Zhijie Sun, Zhicheng Zhou, Suming Qiu, Junjie Huang, Haijia Sun, Linyuan Qiu

机构 * Huawei Technologies Co., Ltd.（华为技术有限公司） 纠错

专题命中 长上下文与记忆 ：large language model(abstract)；language model(abstract)；分类 cs.LG

AgenticAD: A Specialized Multiagent System Framework for Holistic Alzheimer Disease Management

Adib Bazgir, Amir Habibdoust, Xing Song, Yuwen Zhang

专题命中 长上下文与记忆 ：large language model(abstract)；language model(abstract)；分类 cs.AI

COSMOS: A Hybrid Adaptive Optimizer for Memory-Efficient Training of LLMs

Liming Liu, Zhenghao Xu, Zixuan Zhang, Hao Kang, Zichong Li, Chen Liang, Weizhu Chen, Tuo Zhao

机构 * Georgia Tech（佐治亚理工学院） ； Microsoft（微软公司） 纠错

专题命中 长上下文与记忆 ：large language model(abstract)；language model(abstract)；分类 cs.LG

Comments 23 pages, 9 figures, 6 tables

Titans Revisited: A Lightweight Reimplementation and Critical Analysis of a Test-Time Memory Model

Gavriel Di Nepi, Federico Siciliano, Fabrizio Silvestri

机构 * Sapienza University of Rome（罗马萨皮恩扎大学） 纠错

专题命中 长上下文与记忆 ：language model(abstract)；分类 cs.AI、cs.LG

Mem4Nav: Boosting Vision-and-Language Navigation in Urban Environments with a Hierarchical Spatial-Cognition Long-Short Memory System

Lixuan He, Haoyu Dong, Zhenxing Chen, Yangcheng Yu, Jie Feng, Yong Li

专题命中 长上下文与记忆 ：LLM(abstract)；分类 cs.CL、cs.AI

Comments The paper is currently under investigation regarding concerns of potential academic misconduct. While the investigation is ongoing, the authors have voluntarily requested to withdraw the manuscript

AnnaAgent: Dynamic Evolution Agent System with Multi-Session Memory for Realistic Seeker Simulation

Ming Wang, Peidong Wang, Lin Wu, Xiaocui Yang, Daling Wang, Shi Feng, Yuxin Chen, Bixuan Wang, Yifei Zhang

机构 * School of Computer Science and Engineering, Northeastern University（计算机科学与工程学院，东北大学） ； Mental Health Education Center, Northeastern University（心理健康教育中心，东北大学） ； School of Sociology and Psychology, Central University of Finance and Economics（社会学与心理学学院，中央财经大学） ； School of Psychology, Northeast Normal University（心理学学院，东北师范大学） 纠错

专题命中 长上下文与记忆 ：LLM(abstract)；分类 cs.CL、cs.AI

Journal ref Findings of the Association for Computational Linguistics: ACL 2025

Prompting Test-Time Scaling Is A Strong LLM Reasoning Data Augmentation

Sondos Mahmoud Bsharat, Zhiqiang Shen

机构 * MBZUAI 纠错

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

Comments Our code and data are available at https://github.com/VILA-Lab/PTTS

SwarmGPT: Combining Large Language Models with Safe Motion Planning for Drone Swarm Choreography

Martin Schuck, Dinushka Orrin Dahanaggamaarachchi, Ben Sprenger, Vedant Vyas, Siqi Zhou, Angela P. Schoellig

机构 * Learning Systems and Robotics Lab（学习系统与机器人实验室） ； Munich Institute of Robotics and Machine Intelligence（慕尼黑机器人与机器智能研究所） ； Technical University of Munich（慕尼黑技术大学） 纠错

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

Comments Accepted at RA-L 2025

Beyond Surface Reasoning: Unveiling the True Long Chain-of-Thought Capacity of Diffusion Large Language Models

Qiguang Chen, Hanjing Li, Libo Qin, Dengyun Peng, Jinhao Liu, Jiangyi Wang, Chengyue Wu, Xie Chen, Yantao Du, Wanxiang Che

机构 * LARG, Research Center for Social Computing and Interactive Robotics, Harbin Institute of Technology（LARG，社会计算与交互机器人研究中心，哈尔滨工业大学） ； School of Computer Science and Engineering, Central South University（计算机科学与工程学院，中南大学） ； The University of Hong Kong（香港大学） ； Shanghai Jiao Tong University（上海交通大学） ； ByteDance Seed (China)（字节跳动种子（中国）） 纠错

专题命中 推理与问题求解 ：large language model(title,abstract)；language model(title,abstract)；prompting(abstract)；分类 cs.CL

Comments Preprint

AdaReasoner: Adaptive Reasoning Enables More Flexible Thinking in Large Language Models

Xiangqi Wang, Yue Huang, Yanbo Wang, Xiaonan Luo, Kehan Guo, Yujun Zhou, Xiangliang Zhang

机构 * University of Notre Dame（诺丁汉大学） ； MBZUAI（穆桑人工智能研究所） 纠错

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

Reasoning Large Language Model Errors Arise from Hallucinating Critical Problem Features

Alex Heyman, Joel Zylberberg

机构 * Department of Electrical Engineering and Computer Science（电气工程与计算机科学系） ； York University（约克大学） ； Jules Stein Eye Institute（朱利斯·斯坦眼科研究所） ； University of California（加州大学） ； University of California Los Angeles（加州大学洛杉矶分校） 纠错

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

Comments 19 pages (9 excluding references and appendices); 9 figures (6 excluding appendices)