语言大模型 / LLM

2510.16823 2025-11-13 cs.SE cs.CR 67%

When AI Takes the Wheel: Security Analysis of Framework-Constrained Program Generation

Yue Liu, Zhenchang Xing, Shidong Pan, Chakkrit Tantithamthavorn

专题命中指令微调：large language model(abstract)；language model(abstract)

2511.08892 2025-11-13 cs.AI 57%

Lumine: An Open Recipe for Building Generalist Agents in 3D Open Worlds

Weihao Tan, Xiangyang Li, Yunhao Fang, Heyuan Yao, Shi Yan, Hao Luo, Tenglong Ao, Huihui Li, Hongbin Ren, Bairen Yi, Yujia Qin, Bo An, Libin Liu, Guang Shi

机构 * ByteDance Seed（字节跳动种子）； NTU（国立科技大学）

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

2511.09335 2025-11-13 hep-ph hep-ex 50%

A Methodology for Developing Foundational Transformer Models in Collider Physics Analysis

E. Abasov, L. Dudko, E. Iudin, A. Markina, P. Volkov, M. Perfilov, A. Zaborenko

专题命中指令微调：foundation model(abstract)

2510.23658 2025-11-13 cs.LG cs.AI 90%

Aligning Diffusion Language Models via Unpaired Preference Optimization

Vaibhav Jindal, Hejian Sang, Chun-Mao Lai, Yanning Chen, Zhipeng Wang

机构 * LinkedIn Corporation（LinkedIn公司）； University of California San Diego（加州大学圣地亚哥分校）

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

2505.16483 2025-11-13 cs.CL cs.AI 88%

Teaching Large Language Models to Maintain Contextual Faithfulness via Synthetic Tasks and Reinforcement Learning

Shuzheng Si, Haozhe Zhao, Cheng Gao, Yuzhuo Bai, Zhitong Wang, Bofei Gao, Kangyang Luo, Wenhao Li, Yufei Huang, Gang Chen, Fanchao Qi, Minjia Zhang, Baobao Chang, Maosong Sun

机构 * Shuzheng Si（上海交通大学）； Haozhe Zhao（上海交通大学）； Cheng Gao（上海交通大学）； Yuzhuo Bai（上海交通大学）； Zhitong Wang（上海交通大学）； Bofei Gao（上海交通大学）； Kangyang Luo（上海交通大学）； Wenhao Li（上海交通大学）； Yufei Huang（上海交通大学）； Gang Chen（上海交通大学）； Fanchao Qi（上海交通大学）； Minjia Zhang（上海交通大学）； Baobao Chang（上海交通大学）； Maosong Sun（复旦大学）

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

Comments AAAI 2026 (Oral Presentation)

2511.09105 2025-11-13 cs.LG cs.AI 88%

Cost-Minimized Label-Flipping Poisoning Attack to LLM Alignment

Shigeki Kusaka, Keita Saito, Mikoto Kudo, Takumi Tanabe, Akifumi Wachi, Youhei Akimoto

专题命中后训练与偏好优化：LLM(title,abstract)；large language model(abstract)；language model(abstract)；RLHF(abstract)

Comments accepted for AAAI 2026 Special Track on AI Alignment

2412.17417 2025-11-13 cs.CV 82%

Synth-Align: Improving Trustworthiness in Vision-Language Model with Synthetic Preference Data Alignment

Robert Wijaya, Ngoc-Bao Nguyen, Ngai-Man Cheung

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

2511.07419 2025-11-13 cs.LG 77%

Routing Manifold Alignment Improves Generalization of Mixture-of-Experts LLMs

Zhongyang Li, Ziyue Li, Tianyi Zhou

机构 * Johns Hopkins University（约翰霍普金斯大学）； University of Maryland, College Park（马里兰大学学院公园分校）

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

2511.09047 2025-11-13 cs.LG 70%

Preference is More Than Comparisons: Rethinking Dueling Bandits with Augmented Human Feedback

Shengbo Wang, Hong Sun, Ke Li

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

Comments Extended version of our AAAI 2026 paper

2511.08594 2025-11-13 cs.CL 70%

Diverse Preference Learning for Capabilities and Alignment

Stewart Slocum, Asher Parker-Sartori, Dylan Hadfield-Menell

机构 * MIT CSAIL（麻省理工学院计算机科学与人工智能实验室）

专题命中后训练与偏好优化：LLM(abstract)；RLHF(abstract)；分类 cs.CL

Journal ref 13th International Conference on Learning Representations (ICLR 2025)

2511.08835 2025-11-13 cs.CL cs.AI 62%

Beyond Task-Oriented and Chitchat Dialogues: Proactive and Transition-Aware Conversational Agents

Yejin Yoon, Yuri Son, Namyoung So, Minseo Kim, Minsoo Cho, Chanhee Park, Seungshin Lee, Taeuk Kim

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

Comments accepted to EMNLP2025

2509.18542 2025-11-13 cs.LG cs.AI 62%

Symphony-MoE: Harmonizing Disparate Pre-trained Models into a Coherent Mixture-of-Experts

Qi Wang, Hanyang Peng, Yue Yu

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

2511.09516 2025-11-13 cs.RO cs.CV 78%

MAP-VLA: Memory-Augmented Prompting for Vision-Language-Action Model in Robotic Manipulation

Runhao Li, Wenkai Guo, Zhenyu Wu, Changyuan Wang, Haoyuan Deng, Zhenyu Weng, Yap-Peng Tan, Ziwei Wang

机构 * Nanyang Technological University（南洋理工大学）； VinUniversity（文大学）； Beijing University of Posts and Telecommunications（北京邮电大学）； Tsinghua University（清华大学）； South China University of Technology（华南理工大学）

专题命中长上下文与记忆：prompting(title,abstract)

2511.09539 2025-11-13 cs.CL 70%

SynClaimEval: A Framework for Evaluating the Utility of Synthetic Data in Long-Context Claim Verification

Mohamed Elaraby, Jyoti Prakash Maheswari

机构 * University of Pittsburgh（匹兹堡大学）； Zillow Inc.（Zillow公司）

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

Journal ref The 5th Workshop on Evaluation & Comparison of NLP Systems, 2025

2508.10419 2025-11-13 cs.CL cs.AI cs.LG 67%

ComoRAG: A Cognitive-Inspired Memory-Organized RAG for Stateful Long Narrative Reasoning

Juyuan Wang, Rongchen Zhao, Wei Wei, Yufeng Wang, Mo Yu, Jie Zhou, Jin Xu, Liyan Xu

机构 * Tencent（腾讯）

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

Comments Accepted by AAAI 2026

2508.12495 2025-11-13 cs.CL cs.AI cs.LG 91%

Mitigating Hallucinations in Large Language Models via Causal Reasoning

Yuangang Li, Yiqing Shen, Yi Nian, Jiechao Gao, Ziyi Wang, Chenxiao Yu, Shawn Li, Jie Wang, Xiyang Hu, Yue Zhao

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

2511.09381 2025-11-13 cs.CL cs.AI 90%

Self-Correcting Large Language Models: Generation vs. Multiple Choice

Hossein A. Rahmani, Satyapriya Krishna, Xi Wang, Mohammadmehdi Naghiaei, Emine Yilmaz

机构 * University College London（伦敦大学学院）； Amazon AGI（亚马逊人工智能实验室）； University of Sheffield（谢菲尔德大学）； University of Southern California（南加州大学）

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

Comments 20 pages

2507.03133 2025-11-13 cs.CL 89%

ReliableMath: Benchmark of Reliable Mathematical Reasoning on Large Language Models

Boyang Xue, Qi Zhu, Rui Wang, Sheng Wang, Hongru Wang, Minda Hu, Fei Mi, Yasheng Wang, Lifeng Shang, Qun Liu, Kam-Fai Wong

机构 * The Chinese University of Hong Kong（香港中文大学）； Huawei Noah’s Ark Lab（华为诺亚实验室）； The University of Hong Kong（香港大学）

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

Comments under review

2505.15311 2025-11-13 cs.LG cs.AI cs.CL 87%

Trajectory Bellman Residual Minimization: A Simple Value-Based Method for LLM Reasoning

Yurun Yuan, Fan Chen, Zeyu Jia, Alexander Rakhlin, Tengyang Xie

机构 * UW-Madison（威斯康星大学麦迪逊分校）； MIT（麻省理工学院）

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.AI、cs.LG

Comments NeurIPS 2025

2511.08721 2025-11-13 cs.LG cs.AI cs.CL 87%

Benevolent Dictators? On LLM Agent Behavior in Dictator Games

Andreas Einwiller, Kanishka Ghosh Dastidar, Artur Romazanov, Annette Hautli-Janisz, Michael Granitzer, Florian Lemmerich

机构 * University of Passau（帕绍大学）

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.AI、cs.LG

Comments 7 pages, 2 figures, v1 init

2503.01908 2025-11-13 cs.CR cs.AI cs.LG 86%

UDora: A Unified Red Teaming Framework against LLM Agents by Dynamically Hijacking Their Own Reasoning

Jiawei Zhang, Shuang Yang, Bo Li

机构 * Department of Computer Science, University of Chicago（芝加哥大学计算机科学系）； Meta ； Department of Computer Science, University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校计算机科学系）

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

2505.11122 2025-11-13 cs.AI 85%

Navigating the Alpha Jungle: An LLM-Powered MCTS Framework for Formulaic Factor Mining

Yu Shi, Yitong Duan, Jian Li

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

2503.09474 2025-11-13 cs.CV 85%

Surgical AI Copilot: Energy-Based Fourier Gradient Low-Rank Adaptation for Surgical LLM Agent Reasoning and Planning

Jiayuan Huang, Runlong He, Danyal Zaman Khan, Evangelos B. Mazomenos, Danail Stoyanov, Hani Marcus, Linzhe Jiang, Matthew J Clarkson, Mobarak I. Hoque

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

Comments 11 pages

2511.09030 2025-11-13 cs.AI cs.CL cs.MA 81%

Solving a Million-Step LLM Task with Zero Errors

Elliot Meyerson, Giuseppe Paolo, Roberto Dailey, Hormoz Shahrzad, Olivier Francon, Conor F. Hayes, Xin Qiu, Babak Hodjat, Risto Miikkulainen

机构 * Cognizant AI Lab（Cognizant AI实验室）； UT Austin（得克萨斯大学奥斯汀分校）

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

Comments Main paper: 14 pages, 29 pages with references and appendix

2511.09005 2025-11-13 cs.AI cs.CL cs.MA 79%

AI Founding Fathers: A Case Study of GIS Search in Multi-Agent Pipelines

Alvin Chauhan

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

Comments 9 pages, 3 figures. Code and data available at https://github.com/alvco/Founding_Fathers_AI

2511.08596 2025-11-13 cs.CL cs.AI cs.CY 79%

What About the Scene with the Hitler Reference? HAUNT: A Framework to Probe LLMs' Self-consistency Via Adversarial Nudge

Arka Dutta, Sujan Dutta, Rijul Magu, Soumyajit Datta, Munmun De Choudhury, Ashiqur R. KhudaBukhsh

机构 * Rochester Institute of Technology（罗切斯特技术学院）； Georgia Institute of Technology（佐治亚理工学院）

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

2508.06904 2025-11-13 cs.CV 78%

An Instance-Aware Prompting Framework for Training-free Camouflaged Object Segmentation

Chao Yin, Jide Li, Hang Yao, Xiaoqiang Li

机构 * Shanghai University（上海大学）

专题命中推理与问题求解：prompting(title,abstract)

Comments under review

2511.09228 2025-11-13 cs.CV cs.CL 77%

Taming Object Hallucinations with Verified Atomic Confidence Estimation

Jiarui Liu, Weihao Xuan, Zhijing Jin, Mona Diab

机构 * CMU（卡内基梅隆大学）； The University of Tokyo（东京大学）； The University of Toronto（多伦多大学）

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

2509.10975 2025-11-13 cs.IR cs.CL 77%

ReFineG: Synergizing Small Supervised Models and LLMs for Low-Resource Grounded Multimodal NER

Jielong Tang, Shuang Wang, Zhenxing Wang, Jianxing Yu, Jian Yin

机构 * School of Artificial Intelligence, Sun Yat-sen University（中山大学人工智能学院）； Key Laboratory of Sustainable Tourism Smart Assessment Technology, Ministry of Culture and Tourism, Sun Yat-sen University（文化旅游可持续评估技术重点实验室，中华人民共和国文化和旅游部，中山大学）； Beijing Normal University（北京师范大学）； Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所）

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

Comments CCKS 2025 Shared Task Paper

2511.09478 2025-11-13 cs.LG cs.AI cs.CL 75%

AdaCuRL: Adaptive Curriculum Reinforcement Learning with Invalid Sample Mitigation and Historical Revisiting

Renda Li, Hailang Huang, Fei Wei, Feng Xiong, Yong Wang, Xiangxiang Chu

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

1. 指令微调 22 篇