语言大模型 / LLM

Black-Box Guardrail Reverse-engineering Attack

Hongwei Yao, Yun Xia, Shuo Shao, Haoran Shi, Tong Qiao, Cong Wang

机构 * City University of Hong Kong（香港城市大学） ； Zhejiang University（浙江大学） ； Hangzhou Dianzi University（杭州电子科技大学） 纠错

专题命中 效率与部署 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL

Mustafar: Promoting Unstructured Sparsity for KV Cache Pruning in LLM Inference

Donghyeon Joo, Helya Hosseini, Ramyad Hadidi, Bahar Asgari

机构 * Department of Computer Science, University of Maryland（计算机科学系，马里兰大学） ； d-Matrix 纠错

专题命中 效率与部署 ：LLM(title)；分类 cs.LG

Comments 20 pages, 9 figures, NeurIPS 2025

RadZero: Similarity-Based Cross-Attention for Explainable Vision-Language Alignment in Chest X-ray with Zero-Shot Multi-Task Capability

Jonggwon Park, Byungmu Yoon, Soobum Kim, Kyoyun Choi

专题命中 效率与部署 ：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.LG

Comments NeurIPS 2025

Small Singular Values Matter: A Random Matrix Analysis of Transformer Models

Max Staats, Matthias Thamm, Bernd Rosenow

机构 * Center for Scalable Data Analytics and Artificial Intelligence（可扩展数据与人工智能研究中心） ； Leipzig University（莱比锡大学） ； Institute for Theoretical Physics（理论物理研究所） 纠错

专题命中 效率与部署 ：large language model(abstract)；language model(abstract)；分类 cs.LG

Comments 10 pages, 7 figures

Transforming Mentorship: An AI Powered Chatbot Approach to University Guidance

Mashrur Rahman, Mantaqa abedin, Monowar Zamil Abir, Faizul Islam Ansari, Adib Reza, Farig Yousuf Sadeque, Niloy Farhan

机构 * Computer Science and Engineering（计算机科学与工程） ； Brac University（布拉克斯大学） 纠错

专题命中 效率与部署 ：large language model(abstract)；language model(abstract)；分类 cs.CL

Comments 11 pages

Exact Expressive Power of Transformers with Padding

William Merrill, Ashish Sabharwal

机构 * Allen Institute for AI（艾伦人工智能研究所） 纠错

专题命中 效率与部署 ：large language model(abstract)；language model(abstract)；分类 cs.LG

Comments Neurips 2025

SP-MoE: Speculative Decoding and Prefetching for Accelerating MoE-based Model Inference

Liangkun Chen, Zijian Wen, Tian Wu, Xiaoxi Zhang, Chuan Wu

专题命中 效率与部署 ：large language model(abstract)；language model(abstract)

GENIAL: Generative Design Space Exploration via Network Inversion for Low Power Algorithmic Logic Units

Maxence Bouvier, Ryan Amaudruz, Felix Arnold, Renzo Andri, Lukas Cavigelli

机构 * Huawei, Switzerland（华为，瑞士） 纠错

专题命中 效率与部署 ：pretraining(abstract)；分类 cs.AI、cs.LG

Comments Accepted at the 2026 31st Asia and South Pacific Design Automation Conference (ASP-DAC)

Optimizing Reasoning Efficiency through Prompt Difficulty Prediction

Bo Zhao, Berkcan Kapusuzoglu, Kartik Balasubramaniam, Sambit Sahu, Supriyo Chakraborty, Genta Indra Winata

机构 * UC San Diego（加州大学圣地亚哥分校） ； Capital One（Capital One公司） 纠错

专题命中 效率与部署 ：language model(abstract)；分类 cs.AI、cs.LG

Comments NeurIPS 2025 Workshop on Efficient Reasoning

Testora: Using Natural Language Intent to Detect Behavioral Regressions

Michael Pradel

专题命中 效率与部署 ：LLM(abstract)

Comments Accepted at IEEE/ACM International Conference on Software Engineering (ICSE) 2026

A Parallel Region-Adaptive Differential Privacy Framework for Image Pixelization

Ming Liu

专题命中 效率与部署 ：foundation model(abstract)

Large language models surpass domain-specific architectures for antepartum electronic fetal monitoring analysis

Sheng Wong, Ravi Shankar, Beth Albert, Gabriel Davis Jones

机构 * Nuffield Department of Women’s & Reproductive Health University of Oxford（妇女与生殖健康奈菲尔德部门牛津大学） 纠错

专题命中 领域大模型 ：large language model(title,abstract)；language model(title,abstract)；foundation model(abstract)；分类 cs.LG

Comments Preparing for journal

Large Language Models for Cyber Security

Raunak Somani, Aswani Kumar Cherukuri

专题命中 领域大模型 ：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)

Will Large Language Models Transform Clinical Prediction?

Yusuf Yildiz, Goran Nenadic, Meghna Jani, David A. Jenkins

专题命中 领域大模型 ：large language model(title,abstract)；language model(title,abstract)；分类 cs.CL

Comments Published: BMC Diagnostic and Prognostic Research

LLM Targeted Underperformance Disproportionately Impacts Vulnerable Users

Elinor Poole-Dayan, Deb Roy, Jad Kabbara

专题命中 领域大模型 ：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Paper accepted at AAAI 2026

MedSapiens: Taking a Pose to Rethink Medical Imaging Landmark Detection

Marawan Elbatel, Anbang Wang, Keyuan Liu, Kaouther Mouheb, Enrique Almar-Munoz, Lizhuo Lin, Yanqi Yang, Karim Lekadir, Xiaomeng Li

机构 * The Hong Kong University of Science and Technology（香港科技大学） ； The University of Hong Kong（香港大学） ； Erasmus MC（埃因霍温麦斯学院） ； Medical University of Innsbruck（因斯布鲁克医科大学） ； University of Barcelona（巴塞罗那大学） 纠错

专题命中 领域大模型 ：foundation model(abstract)；pretraining(abstract)；分类 cs.AI、cs.LG

Hierarchical Retrieval with Evidence Curation for Open-Domain Financial Question Answering on Standardized Documents

Jaeyoung Choe, Jihoon Kim, Woohwan Jung

机构 * Department of Applied Artificial Intelligence, Hanyang University（应用人工智能系，翰阳大学） 纠错

专题命中 领域大模型 ：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

Comments ACL 2025 (Findings)

META-RAG: Meta-Analysis-Inspired Evidence-Re-Ranking Method for Retrieval-Augmented Generation in Evidence-Based Medicine

Mengzhou Sun, Sendong Zhao, Jianyu Chen, Haochun Wang, Bing Qin

专题命中 领域大模型 ：large language model(abstract)；language model(abstract)；分类 cs.CL

Finetuning LLMs for Human Behavior Prediction in Social Science Experiments

Akaash Kolluri, Shengguang Wu, Joon Sung Park, Michael S. Bernstein

机构 * Stanford University（斯坦福大学） 纠错

专题命中 领域大模型 ：large language model(abstract)；language model(abstract)；分类 cs.LG

Comments 16 pages, 5 figures

Journal ref Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 30084-30099

Decomposed Prompting: Probing Multilingual Linguistic Structure Knowledge in Large Language Models

Ercong Nie, Shuzhou Yuan, Bolei Ma, Helmut Schmid, Michael Färber, Frauke Kreuter, Hinrich Schütze

机构 * Center for Information and Language Processing (CIS)（信息与语言处理中心） ； Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心） ； ScaDS.AI and TU Dresden（ScaDS.AI 和 梅克伦堡-前波美拉尼亚技术大学） ； Department of Statistics, LMU Munich（统计学系，慕尼黑大学） ； University of Maryland, College Park（马里兰大学 College Park 分校） 纠错

专题命中 知识编辑与模型理解 ：prompting(title,abstract)；large language model(title)；language model(title)；分类 cs.CL

Comments Accepted to AACL-IJCNLP 2025 Findings

Explaining Software Vulnerabilities with Large Language Models

Oshando Johnson, Alexandra Fomina, Ranjith Krishnamurthy, Vaibhav Chaudhari, Rohith Kumar Shanmuganathan, Eric Bodden

机构 * Chapman University（查普曼大学） ； Paderborn University（帕德博恩大学） ； University of Oldenburg（奥尔登堡大学） ； Paderborn University and Fraunhofer IEM（帕德博恩大学和弗劳恩霍夫IEM研究所） 纠错

专题命中 知识编辑与模型理解 ：large language model(title,abstract)；language model(title,abstract)；分类 cs.AI

KnowThyself: An Agentic Assistant for LLM Interpretability

Suraj Prasai, Mengnan Du, Ying Zhang, Fan Yang

机构 * Wake Forest University（威克森林大学） ； New Jersey Institute of Technology（新泽西理工学院） 纠错

专题命中 知识编辑与模型理解 ：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI、cs.LG

Comments 5 pages, 1 figure, Accepted for publication at the Demonstration Track of the 40th AAAI Conference on Artificial Intelligence (AAAI 26)

Are language models aware of the road not taken? Token-level uncertainty and hidden state dynamics

Amir Zur, Atticus Geiger, Ekdeep Singh Lubana, Eric Bigelow

机构 * Department of Linguistics, Stanford University（斯坦福大学语言学系） ； Department of Psychology, Harvard University（哈佛大学心理学系） ； Center for Brain Science, Harvard University（哈佛大学脑科学中心） ； Physics of Intelligence Group, NTT Research（NTT研究物理智能小组） 纠错

专题命中 知识编辑与模型理解 ：language model(title,abstract)；分类 cs.CL、cs.AI

GRAD: Graph-Retrieved Adaptive Decoding for Hallucination Mitigation

Manh Nguyen, Sunil Gupta, Dai Do, Hung Le

机构 * Applied Artificial Intelligence Initiative（应用人工智能计划） ； Deakin University（德金大学） 纠错

专题命中 知识编辑与模型理解 ：large language model(abstract)；language model(abstract)；prompting(abstract)；分类 cs.CL、cs.LG

Findings of the Fourth Shared Task on Multilingual Coreference Resolution: Can LLMs Dethrone Traditional Approaches?

Michal Novák, Miloslav Konopík, Anna Nedoluzhko, Martin Popel, Ondřej Pražák, Jakub Sido, Milan Straka, Zdeněk Žabokrtský, Daniel Zeman

机构 * Charles University（查理大学） ； University of West Bohemia（西波西米亚大学） 纠错

专题命中 知识编辑与模型理解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL

Comments Accepted to CODI-CRAC 2025

DAMRO: Dive into the Attention Mechanism of LVLM to Reduce Object Hallucination

Xuan Gong, Tianshi Ming, Xinpeng Wang, Zhihua Wei

机构 * Department of Computer Science and Technology, Tongji University（计算机科学与技术系，同济大学） 纠错

专题命中 知识编辑与模型理解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL

Comments Accepted by EMNLP2024 (Main Conference), add GitHub link

Reasoning Models Hallucinate More: Factuality-Aware Reinforcement Learning for Large Reasoning Models

Junyi Li, Hwee Tou Ng

机构 * Department of Computer Science, National University of Singapore（计算机科学系，新加坡国立大学） 纠错

专题命中 知识编辑与模型理解 ：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

Comments accepted by NeurIPS 2025

Harnessing Structured Knowledge: A Concept Map-Based Approach for High-Quality Multiple Choice Question Generation with Effective Distractors

Nicy Scaria, Silvester John Joseph Kennedy, Diksha Seth, Ananya Thakur, Deepak Subramani

机构 * Indian Institute of Science（印度科学研究院） 纠错

专题命中 知识编辑与模型理解 ：LLM(abstract)；分类 cs.CL、cs.AI

Comments Accepted to ECAI 2025

Journal ref The European Conference on Artificial Intelligence. 413 (2025). pp 4089--4096. IOS Press

Unveiling Deep Semantic Uncertainty Perception for Language-Anchored Multi-modal Vision-Brain Alignment

Zehui Feng, Chenqi Zhang, Mingru Wang, Minuo Wei, Shiwei Cheng, Cuntai Guan, Ting Han

专题命中 知识编辑与模型理解 ：pretraining(abstract)

Comments 30 pages, 16 figures, under review as a conference paper

Transferable & Stealthy Ensemble Attacks: A Black-Box Jailbreaking Framework for Large Language Models

Yiqi Yang, Hongye Fu

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