Výsledky vyhledávání - "Have Jørgensen , Ole"

Report

Improving Activation Steering in Language Models with Mean-Centring

Autor: Jorgensen, Ole, Cope, Dylan, Schoots, Nandi, Shanahan, Murray

Recent work in activation steering has demonstrated the potential to better control the outputs of Large Language Models (LLMs), but it involves finding steering vectors. This is difficult because engineers do not typically know how features are repr

Externí odkaz: http://arxiv.org/abs/2312.03813

Zobrazit plný text záznamu

Report

Self-Consistency of Large Language Models under Ambiguity

Autor: Bartsch, Henning, Jorgensen, Ole, Rosati, Domenic, Hoelscher-Obermaier, Jason, Pfau, Jacob

Large language models (LLMs) that do not give consistent answers across contexts are problematic when used for tasks with expectations of consistency, e.g., question-answering, explanations, etc. Our work presents an evaluation benchmark for self-con

Externí odkaz: http://arxiv.org/abs/2310.13439

Zobrazit plný text záznamu