From Directions to Cones: Exploring Multidimensional Representations of Propositional Facts in LLMs

27 May 2025

Papers citing "From Directions to Cones: Exploring Multidimensional Representations of Propositional Facts in LLMs"

5 / 5 papers shown

Title
Linear Representations of Political Perspective Emerge in Large Language Models Junsol Kim James Evans Aaron Schein 149 7 0 03 Mar 2025
The Geometry of Refusal in Large Language Models: Concept Cones and Representational Independence Tom Wollschlager Jannes Elstner Simon Geisler Vincent Cohen-Addad Stephan Günnemann Johannes Gasteiger LLMSV 118 7 0 24 Feb 2025
Refusal Behavior in Large Language Models: A Nonlinear Perspective Fabian Hildebrandt Andreas K. Maier Patrick Krauss A. Schilling 65 4 0 14 Jan 2025
Do LLMs "know" internally when they follow instructions? Juyeon Heo Christina Heinze-Deml Oussama Elachqar Shirley Ren Udhay Nallasamy Andy Miller Kwan Ho Ryan Chan Jaya Narain 154 10 0 18 Oct 2024
From Yes-Men to Truth-Tellers: Addressing Sycophancy in Large Language Models with Pinpoint Tuning Wei Chen Zhen Huang Liang Xie Binbin Lin Houqiang Li ... Deng Cai Yonggang Zhang Wenxiao Wang Xu Shen Jieping Ye 150 10 0 03 Sep 2024