语言大模型 / LLM

A Cross-Lingual Analysis of Bias in Large Language Models Using Romanian History

Matei-Iulian Cocu, Răzvan-Cosmin Cristia, Adrian Marius Dumitran

机构 * University of Bucharest（布加勒斯特大学） ； Softbinator 纠错

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

Comments 10 pages

DMark: Order-Agnostic Watermarking for Diffusion Large Language Models

Linyu Wu, Linhao Zhong, Wenjie Qu, Yuexin Li, Yue Liu, Shengfang Zhai, Chunhua Shen, Jiaheng Zhang

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

CATMark: A Context-Aware Thresholding Framework for Robust Cross-Task Watermarking in Large Language Models

Yu Zhang, Shuliang Liu, Xu Yang, Xuming Hu

机构 * The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州）） ； South China University of Technology（华南理工大学） 纠错

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

Words That Make Language Models Perceive

Sophie L. Wang, Phillip Isola, Brian Cheung

专题命中 其他LLM ：language model(title,abstract)；LLM(abstract)；large language model(abstract)；prompting(abstract)

Homophily-induced Emergence of Biased Structures in LLM-based Multi-Agent AI Systems

Aliakbar Mehdizadeh, Martin Hilbert

专题命中 其他LLM ：LLM(title,abstract)；large language model(abstract)；language model(abstract)

Comments Accepted for publication in Social Network Analysis and Mining

Not a nuisance but a useful heuristic: Outlier dimensions favor frequent tokens in language models

Iuri Macocco, Nora Graichen, Gemma Boleda, Marco Baroni

机构 * Universitat Pompeu Fabra（庞培法布拉大学） ； ICREA 纠错

专题命中 其他LLM ：language model(title,abstract)；分类 cs.CL、cs.AI

Comments Published as workshop paper at BlackBox NLP 2025

ToolTweak: An Attack on Tool Selection in LLM-based Agents

Jonathan Sneh, Ruomei Yan, Jialin Yu, Philip Torr, Yarin Gal, Sunando Sengupta, Eric Sommerlade, Alasdair Paren, Adel Bibi

机构 * University of Oxford（牛津大学） ； Microsoft（微软公司） 纠错

专题命中 其他LLM ：LLM(title)；分类 cs.AI

Modeling the language cortex with form-independent and enriched representations of sentence meaning reveals remarkable semantic abstractness

Shreya Saha, Shurui Li, Greta Tuckute, Yuanning Li, Ru-Yuan Zhang, Leila Wehbe, Evelina Fedorenko, Meenakshi Khosla

机构 * University of California San Diego（加州大学圣地亚哥分校） ； ShanghaiTech University（上海科技大学） ； Kempner Institute, Harvard University（哈佛大学凯普勒研究所） ； Shanghai Jiao Tong University（上海交通大学） ； Carnegie Mellon University（卡内基梅隆大学） ； Massachusetts Institute of Technology（麻省理工学院） 纠错

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

Modeling the Attack: Detecting AI-Generated Text by Quantifying Adversarial Perturbations

Lekkala Sai Teja, Annepaka Yadagiri, Sangam Sai Anish, Siva Gopala Krishna Nuthakki, Partha Pakray

机构 * Computer Science \& Engineering National Institute of Technology Silchar, India lekkalad\ ug\ ； Computer Science \& Engineering National Institute of Technology Silchar, India annepaka22\ ； Computer Science \& Engineering National Institute of Technology Silchar, India sangams\ ug\ ； Computer Science \& Engineering BML Munjal University Haryana, India ； Computer Science \& Engineering National Institute of Technology Silchar, India 纠错

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

Comments 8 pages, 3 figures

Better Pseudo-labeling with Multi-ASR Fusion and Error Correction by SpeechLLM

Jeena Prakash, Blessingh Kumar, Kadri Hacioglu, Bidisha Sharma, Sindhuja Gopalan, Malolan Chetlur, Shankar Venkatesan, Andreas Stolcke

机构 * Uniphore Systems India & USA（Uniphore系统印度与美国） 纠错

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

Journal ref Proc. Interspeech 2025, pp. 579-583

On the $O(\frac{\sqrt{d}}{K^{1/4}})$ Convergence Rate of AdamW Measured by $\ell_1$ Norm

Huan Li, Yiming Dong, Zhouchen Lin

机构 * Institute of Robotics and Automatic Information Systems, College of Artificial Intelligence, Nankai University, Tianjin, China（机器人与自动信息系统研究所，人工智能学院，南开大学，天津，中国） ； National Key Lab of General AI, School of Intelligence Science and Technology, Peking University, Beijing, China（通用人工智能国家重点实验室，智能科学与技术学院，北京大学，北京，中国） 纠错

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

Comments V2: NeurIPS Camera-Ready. V3: expand upon the conference version by incorporating the analysis of NAdamW

Did Translation Models Get More Robust Without Anyone Even Noticing?

Ben Peters, André F. T. Martins

机构 * Instituto de Telecomunicações（电信研究所） ； Instituto Superior Técnico（技术高等学院） ； Universidade de Lisboa（里斯本大学） ； ELLIS Unit Lisbon (LUMLIS)（里斯本ELLIS单位（LUMLIS）） ； Unbabel 纠错

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

Comments ACL 2025 (Main) camera ready

MaskCD: Mitigating LVLM Hallucinations by Image Head Masked Contrastive Decoding

Jingyuan Deng, Yujiu Yang

机构 * Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院，清华大学） 纠错

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

Comments accepted to emnlp2025 findings

Prototyping Digital Social Spaces through Metaphor-Driven Design: Translating Spatial Concepts into an Interactive Social Simulation

Yoojin Hong, Martina Di Paola, Braahmi Padmakumar, Hwi Joon Lee, Mahnoor Shafiq, Joseph Seering

机构 * Northeastern University（东北大学） 纠错

专题命中 其他LLM ：LLM(abstract)；分类 cs.AI

Comments 25 pages, in submission to CHI 2026

Same Task, Different Circuits: Disentangling Modality-Specific Mechanisms in VLMs

Yaniv Nikankin, Dana Arad, Yossi Gandelsman, Yonatan Belinkov

机构 * Technion – Israel Institute of Technology（技术学院 – 以色列理工学院） ； UC Berkeley（加州大学伯克利分校） 纠错

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

BottleHumor: Self-Informed Humor Explanation using the Information Bottleneck Principle

EunJeong Hwang, Peter West, Vered Shwartz

机构 * University of British Columbia（不列颠哥伦比亚大学） ； Vector Institute for AI（人工智能矢量研究所） 纠错

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

Same old story: Hungary's development over the 2000-2020 period

Zoltan Bartha

专题命中 其他LLM ：prompting(abstract)

Journal ref Theory Methodology Practice, 2022