语言大模型 / LLM

Noise-Robustness Through Noise: A Framework combining Asymmetric LoRA with Poisoning MoE

Zhaokun Wang, Jinyu Guo, Jingwen Pu, Lingfeng Chen, Hongli Pu, Jie Ou, Libo Qin, Wenhong Tian

机构 * School of Information and Software Engineering, University of Electronic Science and Technology of China（信息与软件工程学院，电子科学与技术大学） ； School of Computer Science and Engineering, Central South University（计算机科学与工程学院，中南大学） 纠错

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

Comments Accecpted to NeurIPS 2025

FedDEAP: Adaptive Dual-Prompt Tuning for Multi-Domain Federated Learning

Yubin Zheng, Pak-Hei Yeung, Jing Xia, Tianjie Ju, Peng Tang, Weidong Qiu, Jagath C. Rajapakse

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

专题命中 指令微调 ：language model(abstract)

Comments Accepted at MM 2025

LLM Safety Alignment is Divergence Estimation in Disguise

Rajdeep Haldar, Ziyi Wang, Qifan Song, Guang Lin, Yue Xing

机构 * Department of Statistics, Purdue University（普渡大学统计系） ； Department of Statistics, Michigan State University（密歇根州立大学统计系） 纠错

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

Comments Accepted to NeurIPS 2025

Balancing Act: Prioritization Strategies for LLM-Designed Restless Bandit Rewards

Shresth Verma, Niclas Boehmer, Lingkai Kong, Milind Tambe

机构 * Harvard University, USA（哈佛大学） ； Hasso Plattner Institute, Germany（哈索普拉特纳研究所） 纠错

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

Towards Faithful and Controllable Personalization via Critique-Post-Edit Reinforcement Learning

Chenghao Zhu, Meiling Tao, Tiannan Wang, Dongyi Ding, Yuchen Eleanor Jiang, Wangchunshu Zhou

机构 * The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）） ； University of Electronic Science and Technology of China（电子科技大学） ； South China Agricultural University（华南农业大学） 纠错

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

Comments work in progress

LLMs Encode How Difficult Problems Are

William Lugoloobi, Chris Russell

机构 * University of Oxford（牛津大学） 纠错

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

Understanding Reinforcement Learning for Model Training, and future directions with GRAPE

Rohit Patel

机构 * Rohit Patel（独立研究者） 纠错

专题命中 后训练与偏好优化 ：instruction tuning(abstract)；SFT(abstract)；preference optimization(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 35 pages, 1 figure

DP$^2$O-SR: Direct Perceptual Preference Optimization for Real-World Image Super-Resolution

Rongyuan Wu, Lingchen Sun, Zhengqiang Zhang, Shihao Wang, Tianhe Wu, Qiaosi Yi, Shuai Li, Lei Zhang

机构 * The Hong Kong Polytechnic University（香港理工大学） ； OPPO Research Institute（OPPO研究院） ； City University of Hong Kong（香港城市大学） 纠错

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

Comments Accept by NeurIPS 2025

Ranking-based Preference Optimization for Diffusion Models from Implicit User Feedback

Yi-Lun Wu, Bo-Kai Ruan, Chiang Tseng, Hong-Han Shuai

机构 * Institute of Electrical and Computer Engineering, National Yang Ming Chiao Tung University（电子工程学院，阳明交通大学） 纠错

专题命中 后训练与偏好优化 ：preference optimization(title,abstract)

Post-training for Deepfake Speech Detection

Wanying Ge, Xin Wang, Xuechen Liu, Junichi Yamagishi

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

Comments Corrected previous implementation of EER calculation. Slight numerical changes in some of the results

Introducing Spotlight: A Novel Approach for Generating Captivating Key Information from Documents

Ankan Mullick, Sombit Bose, Rounak Saha, Ayan Kumar Bhowmick, Aditya Vempaty, Prasenjit Dey, Ravi Kokku, Pawan Goyal, Niloy Ganguly

机构 * IIT Kharagpur（印度克达尔普大学） ； Emergence AI 纠错

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

Comments Paper accepted in EMNLP 2025 Main Conference (Full Paper)

Journal ref EMNLP 2025 Main Conference (Full Paper)

Towards Agentic Self-Learning LLMs in Search Environment

Wangtao Sun, Xiang Cheng, Jialin Fan, Yao Xu, Xing Yu, Shizhu He, Jun Zhao, Kang Liu

机构 * The Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences（认知与决策智能复杂系统实验室，自动化研究所，中国科学院） ； School of Artificial Intelligence, University of Chinese Academy of Sciences（人工智能学院，中国科学院大学） ； Xiaohongshu Inc（小红书公司） ； Meituan Inc（美团公司） ； Shanghai Artificial Intelligence Laboratory（上海人工智能实验室） ； Tsinghua University（清华大学） 纠错

专题命中 后训练与偏好优化 ：LLM(abstract)；分类 cs.AI

Memory-Augmented State Machine Prompting: A Novel LLM Agent Framework for Real-Time Strategy Games

Runnan Qi, Yanan Ni, Lumin Jiang, Zongyuan Li, Kuihua Huang, Xian Guo

机构 * National University of Defense Technology（国防科技大学） ； Nankai University（南开大学） 纠错

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

Comments 10 pages, 4 figures, 1 table, 1 algorithm. Submitted to conference

Tree of Agents: Improving Long-Context Capabilities of Large Language Models through Multi-Perspective Reasoning

Song Yu, Xiaofei Xu, Ke Deng, Li Li, Lin Tian

机构 * School of Computer and Information Science, Southwest University（西南大学计算机与信息科学学院） ； School of Information Technology, Murdoch University（默多克大学信息科技学院） ； School of Computing Technologies, RMIT University（皇家墨尔本理工大学计算技术学院） ； University of Technology Sydney（悉尼技术大学） 纠错

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

Comments 19 pages, 5 figures

DrunkAgent: Stealthy Memory Corruption in LLM-Powered Recommender Agents

Shiyi Yang, Zhibo Hu, Xinshu Li, Chen Wang, Tong Yu, Xiwei Xu, Liming Zhu, Lina Yao

机构 * The University of New South Wales（新南威尔士大学） ； Macquarie University（麦考瑞大学） ； Adobe Research（Adobe研究） 纠错

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

Efficient Long-context Language Model Training by Core Attention Disaggregation

Yonghao Zhuang, Junda Chen, Bo Pang, Yi Gu, Yibo Zhu, Yimin Jiang, Ion Stoica, Eric Xing, Hao Zhang

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

Glyph: Scaling Context Windows via Visual-Text Compression

Jiale Cheng, Yusen Liu, Xinyu Zhang, Yulin Fei, Wenyi Hong, Ruiliang Lyu, Weihan Wang, Zhe Su, Xiaotao Gu, Xiao Liu, Yushi Bai, Jie Tang, Hongning Wang, Minlie Huang

机构 * The Conversational Artificial Intelligence (CoAI) Group, Tsinghua University（清华大学对话人工智能（CoAI）小组） ； Zhipu AI（智谱AI） ； The Knowledge Engineering Group (KEG), Tsinghua University（清华大学知识工程小组（KEG）） 纠错

专题命中 长上下文与记忆 ：LLM(abstract)；large language model(abstract)；language model(abstract)；SFT(abstract)

Long-Context Attention Benchmark: From Kernel Efficiency to Distributed Context Parallelism

Tao Bu, Qiangang Wang, Bowen Zeng, Hanwen Sun, Yunpeng Huang, Chun Cao, Jingwei Xu

机构 * State Key Laboratory for Novel Software Technology, Nanjing University, China（南京大学新型软件技术国家重点实验室） ； Zhejiang University, China（浙江大学） ； Peking University, China（北京大学） 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.AI、cs.LG

Comments 56 pages

LLM-RG: Referential Grounding in Outdoor Scenarios using Large Language Models

Pranav Saxena, Avigyan Bhattacharya, Ji Zhang, Wenshan Wang

机构 * Birla Institute of Technology and Science Pilani, K.K Birla Goa Campus（比拉理工学院和科学学院，K.K Birla Goa校区） ； Carnegie Mellon University, Robotics Institute（卡内基梅隆大学，机器人研究所） 纠错

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

Comments Human-aware Embodied AI Workshop @ IROS 2025

Outraged AI: Large language models prioritise emotion over cost in fairness enforcement

Hao Liu, Yiqing Dai, Haotian Tan, Yu Lei, Yujia Zhou, Zhen Wu

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)

Ontology-Enhanced Knowledge Graph Completion using Large Language Models

Wenbin Guo, Xin Wang, Jiaoyan Chen, Zhao Li, Zirui Chen

机构 * Tianjin University, College of Intelligence and Computing（天津大学智能与计算学院） ； University of Manchester, Department of Computer Science（曼彻斯特大学计算机科学系） 纠错

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

Retrieval-in-the-Chain: Bootstrapping Large Language Models for Generative Retrieval

Yingchen Zhang, Ruqing Zhang, Jiafeng Guo, Wenjun Peng, Sen Li, Fuyu Lv

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

Segment Policy Optimization: Effective Segment-Level Credit Assignment in RL for Large Language Models

Yiran Guo, Lijie Xu, Jie Liu, Dan Ye, Shuang Qiu

机构 * Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所） ； University of Chinese Academy of Sciences（中国科学院大学） ； City University of Hong Kong（香港城市大学） 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.CL、cs.AI、cs.LG

Comments Accepted at NeurIPS 2025

Select-Then-Decompose: From Empirical Analysis to Adaptive Selection Strategy for Task Decomposition in Large Language Models

Shuodi Liu, Yingzhuo Liu, Zi Wang, Yusheng Wang, Huijia Wu, Liuyu Xiang, Zhaofeng He

机构 * Beijing University of Posts and Telecommunications（北京邮电大学） 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.CL、cs.AI

Comments Accepted to the Main Conference of EMNLP 2025 (Oral)

Identity-Aware Large Language Models require Cultural Reasoning

Alistair Plum, Anne-Marie Lutgen, Christoph Purschke, Achim Rettinger

机构 * University of Luxembourg, Luxembourg（卢森堡大学） ； Trier University, Germany（特里尔大学） 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.CL

VisuRiddles: Fine-grained Perception is a Primary Bottleneck for Multimodal Large Language Models in Abstract Visual Reasoning

Hao Yan, Xingchen Liu, Hao Wang, Zhenbiao Cao, Handong Zheng, Liang Yin, Xinxing Su, Zihao Chen, Jihao Wu, Minghui Liao, Chao Weng, Wei Chen, Yuliang Liu, Xiang Bai

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

Comments 13 pages, 4 figures

OPTAGENT: Optimizing Multi-Agent LLM Interactions Through Verbal Reinforcement Learning for Enhanced Reasoning

Zhenyu Bi, Meng Lu, Yang Li, Swastik Roy, Weijie Guan, Morteza Ziyadi, Xuan Wang

机构 * Virginia Tech（弗吉尼亚理工大学） ； College of William and Mary（威廉与玛丽学院） ； Amazon Alexa AI（亚马逊Alexa人工智能） 纠错

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

Comments 8 pages for main content

Prompting the Priorities: A First Look at Evaluating LLMs for Vulnerability Triage and Prioritization

Osama Al Haddad, Muhammad Ikram, Ejaz Ahmed, Young Lee

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

Comments 19 pages, 8 figures

Soundness-Aware Level: A Microscopic Signature that Predicts LLM Reasoning Potential

Xuansheng Wu, Xiaoman Pan, Wenlin Yao, Jianshu Chen

机构 * University of Georgia（佐治亚大学） 纠错

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

Comments Pre-print

A$^2$FM: An Adaptive Agent Foundation Model for Tool-Aware Hybrid Reasoning

Qianben Chen, Jingyi Cao, Jiayu Zhang, Tianrui Qin, Xiaowan Li, King Zhu, Dingfeng Shi, He Zhu, Minghao Liu, Xiaobo Liang, Xin Gui, Ge Zhang, Jian Yang, Yuchen Eleanor Jiang, Wangchunshu Zhou

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

Comments 12 pages, 6 figures