语言大模型 / LLM

Scam Shield: Multi-Model Voting and Fine-Tuned LLMs Against Adversarial Attacks

Chen-Wei Chang, Shailik Sarkar, Hossein Salemi, Hyungmin Kim, Shutonu Mitra, Hemant Purohit, Fengxiu Zhang, Michin Hong, Jin-Hee Cho, Chang-Tien Lu

机构 * Department of Computer Science, Virginia Tech, USA（弗吉尼亚理工大学计算机科学系） ； Department of Information Sciences（信息科学系） ； School of Policy and Government, George Mason University, USA（乔治·马歇尔大学政策与政府学院） ； School of Social Work, Indiana University, USA（印第安纳大学社会工作学院） 纠错

专题命中 指令微调 ：LLM(abstract)；分类 cs.AI

Comments 8 pages

EVLP:Learning Unified Embodied Vision-Language Planner with Reinforced Supervised Fine-Tuning

Xinyan Cai, Shiguang Wu, Dafeng Chi, Yuzheng Zhuang, Xingyue Quan, Jianye Hao, Qiang Guan

机构 * Institute of Automation, Chinese Academy of Sciences (CASIA)（中国科学院自动化研究所） 纠错

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

Consistent Story Generation: Unlocking the Potential of Zigzag Sampling

Mingxiao Li, Mang Ning, Marie-Francine Moens

机构 * KU Leuven（库勒芬大学） ； Utrecht University（乌得勒支大学） 纠错

专题命中 指令微调 ：prompting(abstract)

Comments 20 pages, 10 figures

Journal ref published at NeurIPS 2025

AGO: Adaptive Grounding for Open World 3D Occupancy Prediction

Peizheng Li, Shuxiao Ding, You Zhou, Qingwen Zhang, Onat Inak, Larissa Triess, Niklas Hanselmann, Marius Cordts, Andreas Zell

机构 * Mercedes-Benz AG（梅赛德斯-奔驰集团） ； University of Tübingen（图宾根大学） ； Tübingen AI Center（图宾根人工智能中心） ； University of Bonn（波恩大学） ； RPL ； KTH Royal Institute of Technology（皇家理工学院） ； TU Berlin（柏林技术大学） 纠错

专题命中 指令微调 ：language model(abstract)

RedOne 2.0: Rethinking Domain-specific LLM Post-Training in Social Networking Services

Fei Zhao, Chonggang Lu, Haofu Qian, Fangcheng Shi, Zijie Meng, Jianzhao Huang, Xu Tang, Zheyong Xie, Zheyu Ye, Zhe Xu, Yao Hu, Shaosheng Cao

机构 * NLP Team, Xiaohongshu Inc.（小红书研究院自然语言处理团队） 纠错

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

Multi-Reward GRPO Fine-Tuning for De-biasing Large Language Models: A Study Based on Chinese-Context Discrimination Data

Deng Yixuan, Ji Xiaoqiang

机构 * School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen, China（香港中文大学（深圳）科学与工程学院） ； School of Artificial Intelligence, The Chinese University of Hong Kong, Shenzhen, China（香港中文大学（深圳）人工智能学院） ； Shenzhen Institute of Artificial Intelligence and Robotics for Society, China（深圳人工智能与机器人研究院） 纠错

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

Reg-DPO: SFT-Regularized Direct Preference Optimization with GT-Pair for Improving Video Generation

Jie Du, Xinyu Gong, Qingshan Tan, Wen Li, Yangming Cheng, Weitao Wang, Chenlu Zhan, Suhui Wu, Hao Zhang, Jun Zhang

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

Comments The paper is withdrawn due to the need for further revision and verification of experimental results. A revised version will be resubmitted once the updates are completed

Revisiting the Data Sampling in Multimodal Post-training from a Difficulty-Distinguish View

Jianyu Qi, Ding Zou, Wenrui Yan, Rui Ma, Jiaxu Li, Zhijie Zheng, Zhiguo Yang, Rongchang Zhao

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

Comments Accpeted by AAAI 2026

Atomic Consistency Preference Optimization for Long-Form Question Answering

Jingfeng Chen, Raghuveer Thirukovalluru, Junlin Wang, Kaiwei Luo, Bhuwan Dhingra

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

Comments 13 pages, 1 figure

Teaching Pretrained Language Models to Think Deeper with Retrofitted Recurrence

Sean McLeish, Ang Li, John Kirchenbauer, Dayal Singh Kalra, Brian R. Bartoldson, Bhavya Kailkhura, Avi Schwarzschild, Jonas Geiping, Tom Goldstein, Micah Goldblum

机构 * University of Maryland（马里兰大学） ； New York University（纽约大学） ； Lawrence Livermore National Laboratory（劳伦斯利弗莫尔国家实验室） ； University of North Carolina（北卡罗来纳大学） ； ELLIS Institute Tübingen, Max Planck Institute for Intelligent Systems, Tübingen AI Center（图宾根ELLIS研究所、马克斯·普朗克智能系统研究所、图宾根人工智能中心） ； Columbia University（哥伦比亚大学） 纠错

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

Comments code: https://github.com/mcleish7/retrofitting-recurrence, models: https://huggingface.co/collections/tomg-group-umd/retrofitting-recurrence

GRAPH-GRPO-LEX: Contract Graph Modeling and Reinforcement Learning with Group Relative Policy Optimization

Moriya Dechtiar, Daniel Martin Katz, Mari Sundaresan, Sylvain Jaume, Hongming Wang

机构 * Harvard University（哈佛大学） ； Illinois Tech - Chicago Kent College of Law（伊利诺伊理工学院-芝加哥肯特法学院） ； CLTDS, Bucerius Law School（CLTDS，布塞里乌斯法学院） ； Yong Pung How School of Law, Singapore Management University（永丰何法学院，新加坡管理大学） ； CodeX - The Stanford Center for Legal Informatics, Stanford University（CodeX-斯坦福法律信息中心，斯坦福大学） ； Georgetown University（乔治城大学） ； Massachusetts Institute of Technology（麻省理工学院） 纠错

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

Personalized Image Editing in Text-to-Image Diffusion Models via Collaborative Direct Preference Optimization

Connor Dunlop, Matthew Zheng, Kavana Venkatesh, Pinar Yanardag

机构 * Virginia Tech（弗吉尼亚理工大学） 纠错

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

Comments Published at NeurIPS'25 Main Conference

REINFORCE++: Stabilizing Critic-Free Policy Optimization with Global Advantage Normalization

Jian Hu, Jason Klein Liu, Haotian Xu, Wei Shen

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

Comments refactor

Discourse Graph Guided Document Translation with Large Language Models

Viet-Thanh Pham, Minghan Wang, Hao-Han Liao, Thuy-Trang Vu

机构 * Department of Data Science & AI, Monash University（数据科学与人工智能系，莫纳什大学） 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.CL、cs.AI

Controllable Hybrid Captioner for Improved Long-form Video Understanding

Kuleen Sasse, Efsun Sarioglu Kayi, Arun Reddy

机构 * Johns Hopkins University Applied Physics Laboratory（约翰霍普金斯大学应用物理实验室） 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

MobA: Multifaceted Memory-Enhanced Adaptive Planning for Efficient Mobile Task Automation

Zichen Zhu, Hao Tang, Yansi Li, Dingye Liu, Hongshen Xu, Kunyao Lan, Danyang Zhang, Yixuan Jiang, Hao Zhou, Chenrun Wang, Situo Zhang, Liangtai Sun, Yixiao Wang, Yuheng Sun, Lu Chen, Kai Yu

机构 * Shanghai Jiao Tong University（上海交通大学） 纠错

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

Comments NAACL 2025 Demo Track [code] https://github.com/OpenDFM/MobA [dataset] https://huggingface.co/datasets/OpenDFM/MobA-MobBench

BEE-RAG: Balanced Entropy Engineering for Retrieval-Augmented Generation

Yuhao Wang, Ruiyang Ren, Yucheng Wang, Jing Liu, Wayne Xin Zhao, Hua Wu, Haifeng Wang

机构 * Baidu（百度） 纠错

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

Retrieval Quality at Context Limit

Max McKinnon

机构 * Google LLC Mountain View, U.S.A.（谷歌公司山景城美国分部） 纠错

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

Comments 3 pages, 0 figures

PanoNav: Mapless Zero-Shot Object Navigation with Panoramic Scene Parsing and Dynamic Memory

Qunchao Jin, Yilin Wu, Changhao Chen

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

Comments Accepted as a poster in AAAI 2026

Q-RAG: Long Context Multi-step Retrieval via Value-based Embedder Training

Artyom Sorokin, Nazar Buzun, Alexander Anokhin, Oleg Inozemcev, Egor Vedernikov, Petr Anokhin, Mikhail Burtsev, Trushkov Alexey, Yin Wenshuai, Evgeny Burnaev

机构 * AXXX ； Applied AI Institute（应用人工智能研究所） ； Research Center of the Artificial Intelligence Institute（人工智能研究所研究部） ； London Institute for Mathematical Sciences（伦敦数学科学研究所） ； Higher School of Economics（高等经济学院） 纠错

专题命中 长上下文与记忆 ：LLM(abstract)；分类 cs.LG

Comments 16 pages, 3 figures, 2 tables

Learned Structure in Cartridges: Keys as Shareable Routers in Self-Studied Representations

Maurizio Diaz

专题命中 长上下文与记忆 ：LLM(abstract)；分类 cs.LG

Cross-Modal Unlearning via Influential Neuron Path Editing in Multimodal Large Language Models

Kunhao Li, Wenhao Li, Di Wu, Lei Yang, Jun Bai, Ju Jia, Jason Xue

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

Comments Accepted at AAAI 2026 as a Conference Paper (Oral Presentation)

What Makes Reasoning Invalid: Echo Reflection Mitigation for Large Language Models

Chen He, Xun Jiang, Lei Wang, Hao Yang, Chong Peng, Peng Yan, Fumin Shen, Xing Xu

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.AI、cs.LG

C3PO: Optimized Large Language Model Cascades with Probabilistic Cost Constraints for Reasoning

Antonios Valkanas, Soumyasundar Pal, Pavel Rumiantsev, Yingxue Zhang, Mark Coates

机构 * McGill University（麦吉尔大学） ； Mila - Quebec AI Institute（魁北克AI研究所） ； Int. Lab. Learning Systems（国际学习系统实验室） ； Huawei Montréal, Canada（华为蒙特利尔加拿大分公司） 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.LG

Evaluating the Ability of Large Language Models to Reason about Cardinal Directions, Revisited

Anthony G Cohn, Robert E Blackwell

机构 * School of Computer Science, University of Leeds, UK（利兹大学计算机科学学院） ； Alan Turing Institute, London, UK（艾伦·图灵研究所） 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

Comments 8 pages, 5 figures. Accepted at QR 2025 : 38th International Workshop on Qualitative Reasoning at IJCAI. arXiv admin note: substantial text overlap with arXiv:2406.16528

RadioSim Agent: Combining Large Language Models and Deterministic EM Simulators for Interactive Radio Map Analysis

Sajjad Hussain, Conor Brennan

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

Comments Submitted to EuCAP 2026

TimeSense:Making Large Language Models Proficient in Time-Series Analysis

Zhirui Zhang, Changhua Pei, Tianyi Gao, Zhe Xie, Yibo Hao, Zhaoyang Yu, Longlong Xu, Tong Xiao, Jing Han, Dan Pei

机构 * Tsinghua University（清华大学） ； Computer Network Information Center, Chinese Academy of Sciences（中国科学院计算机网络信息中心） ； ZTE Corporation（中兴通讯） 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

AgentSUMO: An Agentic Framework for Interactive Simulation Scenario Generation in SUMO via Large Language Models

Minwoo Jeong, Jeeyun Chang, Yoonjin Yoon

机构 * Graduate School of Data Science, Korea Advanced Institute of Science and Technology（数据科学研究生院，韩国科学技术院） ； Department of Civil and Environmental Engineering, Korea Advanced Institute of Science and Technology（土木与环境工程系，韩国科学技术院） 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

Comments Submitted to Transportation Research Part C (under review)

SAR-LM: Symbolic Audio Reasoning with Large Language Models

Termeh Taheri, Yinghao Ma, Emmanouil Benetos

机构 * School of Electronic Engineering（电子工程学院） ； Computer Science, Queen Mary University of London, London, United Kingdom（计算机科学，伦敦大学玛丽女王学院，伦敦，英国） 纠错

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

MLLM-For3D: Adapting Multimodal Large Language Model for 3D Reasoning Segmentation

Jiaxin Huang, Runnan Chen, Ziwen Li, Zhengqing Gao, Xiao He, Yandong Guo, Mingming Gong, Tongliang Liu

机构 * MBZUAI ； The University of Sydney（悉尼大学） ； The University of Melbourne（墨尔本大学） ； AI2Robotic 纠错

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

Comments 10 pages, 3 figures