Refusal in Language Models Is Mediated by a Single Direction (arxiv.org) | HN Screenshots

YHacker Newsscreenshots

Screenshot of arxiv.org: Refusal in Language Models Is Mediated by a Single Direction

First screen, captured 5 months ago.

Looks similar

Screenshot of arxiv.org: Refusal in language models is mediated by a single direction

Refusal in language models is mediated by a single direction (arxiv.org)

181 points by Tomte 2 years ago | 40 comments

Screenshot of arxiv.org: Recursive Language Models

Recursive Language Models (arxiv.org)

135 points by schmuhblaster 9 months ago | 23 comments

Screenshot of arxiv.org: A sleep-like consolidation mechanism for LLMs

A sleep-like consolidation mechanism for LLMs (arxiv.org)

178 points by juxtapose 5 months ago | 126 comments

Screenshot of arxiv.org: Language models are injective and hence invertible

Language models are injective and hence invertible (arxiv.org)

194 points by mazsa 1 year ago | 136 comments

Screenshot of arxiv.org: Unsupervised Elicitation of Language Models

Unsupervised Elicitation of Language Models (arxiv.org)

128 points by kordlessagain 1 year ago | 18 comments

Screenshot of arxiv.org: AnyMAL: An Efficient and Scalable Any-Modality Augmented Language Model

AnyMAL: An Efficient and Scalable Any-Modality Augmented Language Model (arxiv.org)

26 points by babakd 3 years ago | 4 comments