语言大模型 / LLM

TruthfulRAG: Resolving Factual-level Conflicts in Retrieval-Augmented Generation with Knowledge Graphs

Shuyi Liu, Yuming Shang, Xi Zhang

机构 * Shuyi Liu, Yuming Shang, Xi Zhang（作者） 纠错

专题命中 其他LLM ：large language model(abstract)；language model(abstract)；分类 cs.CL

Comments 12 pages, 3 figures, accepted at AAAI 2026

Order Matters: Rethinking Prompt Construction in In-Context Learning

Warren Li, Yiqian Wang, Zihan Wang, Jingbo Shang

机构 * UC San Diego（圣迭戈大学） ； Cushing Academy（克什克尔学院） 纠错

专题命中 其他LLM ：large language model(abstract)；language model(abstract)；分类 cs.CL

Bilinear Sequence Regression: A Model for Learning from Long Sequences of High-dimensional Tokens

Vittorio Erba, Emanuele Troiani, Luca Biggio, Antoine Maillard, Lenka Zdeborová

机构 * Statistical Physics of Computation Laboratory, École Polytechnique Fédérale de Lausanne (EPFL), Switzerland ； Department of Computing Sciences, Universita Bocconi, Milan, Italy ； Department of Mathematics, ETH Zürich, Switzerland 纠错

专题命中 其他LLM ：large language model(abstract)；language model(abstract)；分类 cs.LG

Journal ref Phys. Rev. X 15, 021092 (2025)

rLLM: Relational Table Learning with LLMs

Weichen Li, Xiaotong Huang, Jianwu Zheng, Zheng Wang, Chaokun Wang, Li Pan, Jianhua Li

机构 * Shanghai Jiao Tong University（上海交通大学） ； Tsinghua University（清华大学） 纠错

专题命中 其他LLM ：large language model(abstract)；language model(abstract)；分类 cs.AI

Understanding and Controlling Repetition Neurons and Induction Heads in In-Context Learning

Nhi Hoai Doan, Tatsuya Hiraoka, Kentaro Inui

机构 * Mohamed bin Zayed University of Artificial Intelligence（Mohamed bin Zayed人工智能大学） ； RIKEN（日本理化学研究所） 纠错

专题命中 其他LLM ：large language model(abstract)；language model(abstract)；分类 cs.CL

Secure Retrieval-Augmented Generation against Poisoning Attacks

Zirui Cheng, Jikai Sun, Anjun Gao, Yueyang Quan, Zhuqing Liu, Xiaohua Hu, Minghong Fang

机构 * National University of Singapore（新加坡国立大学） ； University of Louisville（路易斯维尔大学） ； University of North Texas（北卡罗来纳州立大学） ； Drexel University（德雷塞尔大学） 纠错

专题命中 其他LLM ：large language model(abstract)；language model(abstract)；分类 cs.LG

Comments To appear in IEEE BigData 2025

Decomate: Leveraging Generative Models for Co-Creative SVG Animation

Jihyeon Park, Jiyoon Myung, Seone Shin, Jungki Son, Joohyung Han

机构 * MODULABS 纠错

专题命中 其他LLM ：large language model(abstract)；language model(abstract)；分类 cs.AI

Comments Accepted at the 1st Workshop on Generative and Protective AI for Content Creation (NeurIPS 2025)

Beyond Parallelism: Synergistic Computational Graph Effects in Multi-Head Attention

Haitz Sáez de Ocáriz Borde

机构 * Supermodel 纠错

专题命中 其他LLM ：large language model(abstract)；language model(abstract)；分类 cs.LG

Comments 16 pages, 4 figures, 6 tables. Accepted at NeurIPS 2025 Workshop on Symmetry and Geometry in Neural Representations

Usando LLMs para Programar Jogos de Tabuleiro e Variações

Álvaro Guglielmin Becker, Lana Bertoldo Rossato, Anderson Rocha Tavares

专题命中 其他LLM ：large language model(abstract)；language model(abstract)；分类 cs.LG

Comments Accepted for presentation at the I Escola Regional de Aprendizado de Máquina e Inteligência Artificial da Região Sul, 2025, in Portuguese language

The truth is no diaper: Human and AI-generated associations to emotional words

Špela Vintar, Jan Jona Javoršek

机构 * University of Ljubljana, Slovenia（卢布尔雅那大学） ； Jožef Stefan Institute, Ljubljana, Slovenia（Jožef Stefan研究所） 纠错

专题命中 其他LLM ：large language model(abstract)；language model(abstract)；分类 cs.CL

Comments 6 pages, 1 figure. Presented at ICCC'25, Campinas, Brazil

Erasing 'Ugly' from the Internet: Propagation of the Beauty Myth in Text-Image Models

Tanvi Dinkar, Aiqi Jiang, Gavin Abercrombie, Ioannis Konstas

机构 * Interaction Lab, Heriot Watt University（赫瑞瓦德大学交互实验室） 纠错

专题命中 其他LLM ：language model(abstract)；prompting(abstract)；分类 cs.CL

Comments This is a preprint under review

Language Arithmetics: Towards Systematic Language Neuron Identification and Manipulation

Daniil Gurgurov, Katharina Trinley, Yusser Al Ghussin, Tanja Baeumel, Josef van Genabith, Simon Ostermann

机构 * Saarland University（萨尔兰大学） ； German Research Center for AI (DFKI)（德国人工智能研究中心） ； Centre for European Research in Trusted AI (CERTAIN)（可信人工智能欧洲研究中心） 纠错

专题命中 其他LLM ：large language model(abstract)；language model(abstract)；分类 cs.CL

Comments accepted to AACL main

Generative AI and Empirical Software Engineering: A Paradigm Shift

Christoph Treude, Margaret-Anne Storey

机构 * School of Computing（计算学院） ； Information Systems Singapore Management University Singapore, Singapore（信息系统新加坡管理大学新加坡） ； Department of Computer Science University of Victoria Victoria, Canada（计算机科学系维多利亚大学加拿大） 纠错

专题命中 其他LLM ：large language model(abstract)；language model(abstract)；分类 cs.AI

Comments Published at 2nd IEEE/ACM International Conference on AI-powered Software (AIware 2025)

Generative human motion mimicking through feature extraction in denoising diffusion settings

Alexander Okupnik, Johannes Schneider, Kyriakos Flouris

机构 * University of Liechtenstein（列支敦士登大学） ； University of Cambridge（剑桥大学） 纠错

专题命中 其他LLM ：large language model(abstract)；language model(abstract)；分类 cs.AI

Who Has The Final Say? Conformity Dynamics in ChatGPT's Selections

Clarissa Sabrina Arlinghaus, Tristan Kenneweg, Barbara Hammer, Günter W. Maier

机构 * Bielefeld University（比勒菲尔德大学） 纠错

专题命中 其他LLM ：large language model(abstract)；language model(abstract)；分类 cs.AI

Comments 5 pages, 5 figures, HAI 2025: Workshop on Socially Aware and Cooperative Intelligent Systems

Reflection on Data Storytelling Tools in the Generative AI Era from the Human-AI Collaboration Perspective

Haotian Li, Yun Wang, Huamin Qu

机构 * Microsoft Research Asia（微软亚洲研究院） ； The Hong Kong University of Science and Technology（香港科技大学） 纠错

专题命中 其他LLM ：large language model(abstract)；language model(abstract)；分类 cs.AI

Comments This paper is a sequel to the CHI 24 paper "Where Are We So Far? Understanding Data Storytelling Tools from the Perspective of Human-AI Collaboration (https://doi.org/10.1145/3613904.3642726), aiming to refresh our understanding with the latest advancements. It is accepted at IEEE VIS 25

V-SAT: Video Subtitle Annotation Tool

Arpita Kundu, Joyita Chakraborty, Anindita Desarkar, Aritra Sen, Srushti Anil Patil, Vishwanathan Raman

机构 * LTIMindTree 纠错

专题命中 其他LLM ：large language model(abstract)；language model(abstract)；分类 cs.LG

LASER: A Neuro-Symbolic Framework for Learning Spatial-Temporal Scene Graphs with Weak Supervision

Jiani Huang, Ziyang Li, Mayur Naik, Ser-Nam Lim

机构 * University of Pennsylvania（宾夕法尼亚大学） ； University of Central Florida（中央佛罗里达大学） 纠错

专题命中 其他LLM ：large language model(abstract)；language model(abstract)；分类 cs.LG

Comments Accepted at International Conference on Learning Representations (ICLR) 2025

Are LLMs Empathetic to All? Investigating the Influence of Multi-Demographic Personas on a Model's Empathy

Ananya Malik, Nazanin Sabri, Melissa Karnaze, Mai Elsherief

机构 * Northeastern University（东北大学） ； University of California, San Diego（加州大学圣地亚哥分校） 纠错

专题命中 其他LLM ：large language model(abstract)；language model(abstract)；分类 cs.CL

Comments 9 pages, 4 figures, 4 tables, EMNLP 2025 Findings

Improving Model Fusion by Training-time Neuron Alignment with Fixed Neuron Anchors

Zexi Li, Zhiqi Li, Jie Lin, Tao Shen, Jun Xiao, Yike Guo, Tao Lin, Chao Wu

机构 * Zhejiang University（浙江大学） ； Georgia Institute of Technology（佐治亚理工学院） ； Westlake University（西湖大学） ； Hong Kong University of Science and Technology（香港科技大学） 纠错

专题命中 其他LLM ：language model(abstract)；foundation model(abstract)；分类 cs.LG

Comments IEEE Transactions on Pattern Analysis and Machine Intelligence

Knocking-Heads Attention

Zhanchao Zhou, Xiaodong Chen, Haoxing Chen, Zhenzhong Lan, Jianguo Li

机构 * Ant Group（蚂蚁集团） ； Zhejiang University（浙江大学） ； Westlake University（西湖大学） ； Renmin University of China（中国人民大学） 纠错

专题命中 其他LLM ：large language model(abstract)；language model(abstract)；分类 cs.CL

ColorEcosystem: Powering Personalized, Standardized, and Trustworthy Agentic Service in massive-agent Ecosystem

Fangwen Wu, Zheng Wu, Jihong Wang, Yunku Chen, Ruiguang Pei, Heyuan Huang, Xin Liao, Xingyu Lou, Huarong Deng, Zhihui Fu, Weiwen Liu, Zhuosheng Zhang, Weinan Zhang, Jun Wang

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

专题命中 其他LLM ：large language model(abstract)；language model(abstract)；分类 cs.CL

E2E Process Automation Leveraging Generative AI and IDP-Based Automation Agent: A Case Study on Corporate Expense Processing

Cheonsu Jeong, Seongmin Sim, Hyoyoung Cho, Sungsu Kim, Byounggwan Shin

专题命中 其他LLM ：large language model(abstract)；language model(abstract)；分类 cs.AI

Journal ref 2025, Artificial Intelligence and Applications

Gatsby Without the 'E': Crafting Lipograms with LLMs

Rohan Balasubramanian, Nitish Gokulakrishnan, Syeda Jannatus Saba, Steven Skiena

机构 * Stony Brook University（石溪大学） 纠错

专题命中 其他LLM ：large language model(abstract)；language model(abstract)；分类 cs.CL

KL-Regularized Reinforcement Learning is Designed to Mode Collapse

Anthony GX-Chen, Jatin Prakash, Jeff Guo, Rob Fergus, Rajesh Ranganath

机构 * New York University（纽约大学） ； École Polytechnique Fédérale de Lausanne（瑞士联邦理工学院） 纠错

专题命中 其他LLM ：large language model(abstract)；language model(abstract)；分类 cs.LG

The Lock-In Phase Hypothesis: Identity Consolidation as a Precursor to AGI

Marcelo Maciel Amaral, Raymond Aschheim

机构 * Gauge Freedom, Inc. (Public Benefit Corporation)（Gauge Freedom公司） 纠错

专题命中 其他LLM ：large language model(abstract)；language model(abstract)；分类 cs.AI

Towards Better Health Conversations: The Benefits of Context-seeking

Rory Sayres, Yuexing Hao, Abbi Ward, Amy Wang, Beverly Freeman, Serena Zhan, Diego Ardila, Jimmy Li, I-Ching Lee, Anna Iurchenko, Siyi Kou, Kartikeya Badola, Jimmy Hu, Bhawesh Kumar, Keith Johnson, Supriya Vijay, Justin Krogue, Avinatan Hassidim, Yossi Matias, Dale R. Webster, Sunny Virmani, Yun Liu, Quang Duong, Mike Schaekermann

机构 * Google Research（谷歌研究） 纠错

专题命中 其他LLM ：large language model(abstract)；language model(abstract)；分类 cs.CL

Online Learning Defense against Iterative Jailbreak Attacks via Prompt Optimization

Masahiro Kaneko, Zeerak Talat, Timothy Baldwin

机构 * MBZUAI（马克斯·普朗克人工智能研究所） ； University of Edinburgh（爱丁堡大学） 纠错

专题命中 其他LLM ：large language model(abstract)；language model(abstract)；分类 cs.CL

Who Taught the Lie? Responsibility Attribution for Poisoned Knowledge in Retrieval-Augmented Generation

Baolei Zhang, Haoran Xin, Yuxi Chen, Zhuqing Liu, Biao Yi, Tong Li, Lihai Nie, Zheli Liu, Minghong Fang

机构 * Nankai University（南开大学） ； University of North Texas（北德克萨斯大学） ； University of Louisville（路易斯维尔大学） 纠错

专题命中 其他LLM ：large language model(abstract)；language model(abstract)；分类 cs.LG

Comments To appear in the IEEE Symposium on Security and Privacy, 2026

Unifying Attention Heads and Task Vectors via Hidden State Geometry in In-Context Learning

Haolin Yang, Hakaze Cho, Yiqiao Zhong, Naoya Inoue

机构 * University of Chicago（芝加哥大学） ； JAIST ； University of Wisconsin - Madison（威斯康星大学麦迪逊分校） ； RIKEN（日本研究机构） 纠错

专题命中 其他LLM ：large language model(abstract)；language model(abstract)；分类 cs.CL

Comments 52 pages, 70 figures, 24 tables, NeurIPS 2025