语言大模型 / LLM

Feature Hedging: Correlated Features Break Narrow Sparse Autoencoders

David Chanin, Tomáš Dulka, Adrià Garriga-Alonso

机构 * University College London（伦敦大学学院） ； FAR AI（FAR人工智能） 纠错

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

Technology as uncharted territory: Contextual integrity and the notion of AI as new ethical ground

Alexander Martin Mussgnug

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

Comments Please cite published version

Journal ref Philosophy & Technology 2025

Design Exploration of AI-assisted Personal Affective Physicalization

Ruishan Wu, Zhuoyang Li, Charles Perin, Sheelagh Carpendale, Can Liu

专题命中 其他LLM ：LLM(abstract)