语言大模型 / LLM

Explanation-Driven Counterfactual Testing for Faithfulness in Vision-Language Model Explanations

Sihao Ding, Santosh Vasa, Aditi Ramadwar

机构 * Mercedes-Benz Research & Development North America（梅赛德斯-奔驰研究与开发北美） 纠错

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

Comments NeurIPS 2025 workshop on Regulatable ML

Explaining novel senses using definition generation with open language models

Mariia Fedorova, Andrey Kutuzov, Francesco Periti, Yves Scherrer

机构 * University of Oslo（奥斯陆大学） ； KU Leuven - Flanders Make（库尔勒文大学-佛兰德斯制造） 纠错

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

Comments EMNLP 2025 Findings

SafePassage: High-Fidelity Information Extraction with Black Box LLMs

Joe Barrow, Raj Patel, Misha Kharkovski, Ben Davies, Ryan Schmitt

机构 * Pattern Data 纠错

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

Phantom: General Backdoor Attacks on Retrieval Augmented Language Generation

Harsh Chaudhari, Giorgio Severi, John Abascal, Anshuman Suri, Matthew Jagielski, Christopher A. Choquette-Choo, Milad Nasr, Cristina Nita-Rotaru, Alina Oprea

机构 * Northeastern University（东北大学） ； OpenAI 纠错

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

Safety Instincts: LLMs Learn to Trust Their Internal Compass for Self-Defense

Guobin Shen, Dongcheng Zhao, Haibo Tong, Jindong Li, Feifei Zhao, Yi Zeng

机构 * Beijing Institute of AI Safety and Governance（北京人工智能安全与治理研究院） ； Beijing Key Laboratory of Safe AI and Superalignment（北京安全人工智能与超对齐重点实验室） ； BrainCog Lab, Institute of Automation, Chinese Academy of Sciences（脑认知实验室，中国科学院自动化研究所） 纠错

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

Automatically Generating Web Applications from Requirements Via Multi-Agent Test-Driven Development

Yuxuan Wan, Tingshuo Liang, Jiakai Xu, Jingyu Xiao, Yintong Huo, Michael R. Lyu

机构 * The Chinese University of Hong Kong（香港中文大学） ； Columbia University in the City of New York（哥伦比亚大学） ； Singapore Management University（新加坡管理学院） 纠错

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

Dirichlet-Prior Shaping: Guiding Expert Specialization in Upcycled MoEs

Leyla Mirvakhabova, Babak Ehteshami Bejnordi, Gaurav Kumar, Hanxue Liang, Wanru Zhao, Paul Whatmough

机构 * Qualcomm AI Research（高通人工智能研究） 纠错

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

CodeGenLink: A Tool to Find the Likely Origin and License of Automatically Generated Code

Daniele Bifolco, Guido Annicchiarico, Pierluigi Barbiero, Massimiliano Di Penta, Fiorella Zampetti

机构 * University of Sannio, Italy（萨尼亚大学） 纠错

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

Comments Proceedings of the 40th IEEE/ACM International Conference on Automated Software Engineering (ASE 2025), November 16-20 2025, Seoul, South Korea

Data Quality Challenges in Retrieval-Augmented Generation

Leopold Müller, Joshua Holstein, Sarah Bause, Gerhard Satzger, Niklas Kühl

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

Comments Preprint version. Accepted for presentation at the International Conference on Information Systems (ICIS 2025). Please cite the published version when available

Data driven approaches in nanophotonics: A review of AI-enabled metadevices

Huanshu Zhang, Lei Kang, Sawyer D. Campbell, Jacob T. Young, Douglas H. Werner

机构 * Department of Electrical Engineering（电气工程系） ； The Pennsylvania State University（宾夕法尼亚州立大学） 纠错

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

Reinforcement Learning-Based Prompt Template Stealing for Text-to-Image Models

Xiaotian Zou

机构 * Xiaotian Zou 纠错

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

Comments 10 pages, 3 figures

GenIA-E2ETest: A Generative AI-Based Approach for End-to-End Test Automation

Elvis Júnior, Alan Valejo, Jorge Valverde-Rebaza, Vânia de Oliveira Neves

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

Comments Preprint of a paper published at the 39th Brazilian Symposium on Software Engineering (SBES 2025). Please cite the published version: https://sol.sbc.org.br/index.php/sbes/article/view/37006

Secure coding for web applications: Frameworks, challenges, and the role of LLMs

Kiana Kiashemshaki, Mohammad Jalili Torkamani, Negin Mahmoudi

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

Comments 11 pages, 5 figures, 3 tables, 6 listings

The Self-Contained Negation Test Set

David Kletz, Pascal Amsili, Marie Candito

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

Journal ref BlackboxNLP 2024, BlackboxNLP, Dec 2023, Singapour, Singapore. pp.212-221

Anomalous low-field magnetoresistance in Fe$_3$Ga$_4$ single crystals

Michelle E. Jamer, Gregory M. Stephen, Brandon Wilfong, Radhika Barua, Frank M. Abel, Steven P. Bennett, Joseph C. Prestigiacomo, Don Heiman, Dave Graf

专题命中 其他LLM ：prompting(abstract)

HLTCOE at TREC 2024 NeuCLIR Track

Eugene Yang, Dawn Lawrie, Orion Weller, James Mayfield

专题命中 其他LLM ：LLM(abstract)

Comments TREC 2024 System Paper; 6 pages; 7 tables

DACoN: DINO for Anime Paint Bucket Colorization with Any Number of Reference Images

Kazuma Nagata, Naoshi Kaneko

机构 * Tokyo Denki University（东京电讯大学） 纠错

专题命中 其他LLM ：foundation model(abstract)

Comments Accepted to ICCV 2025. v2: Added results on the subset used by the baseline for consistency; full test set results are also reported (Tables 1 and 2)