◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Owain Evans

Truthful AI

10 papers hereh-index 2410.8k citations33 works total

Matching runs newest-first, so older work may not be attached to this profile yet.

author position
  • middle author2
  • last author6

Across the 8 of 10 papers where every author was matched, so the position is known.

fields
  • cs.CL5
  • cs.LG3
  • cs.AI1
  • cs.CR1
affiliations
  • Truthful AI
  • UC Berkeley
Homepage
same name
  • Owain Evans — 6 papers, h 5
  • Owain Evans — 3 papers, h 3
  • Owain Evans — 2 papers, h 3
  • Owain Evans — 1 paper

Either other researchers who publish under this name, or the same person where the external sources have not merged their records.

identity via Semantic Scholar / OpenAlex

activity
20242026
most citedEmergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs

22 citations · 22 across the 1 of their papers we have counts for

collaborators
Showing cs.CRShow all

1 paper · 1 filter

cs.CR2024

Towards evaluations-based safety cases for AI scheming

Mikita Balesni, Marius Hobbhahn, David Lindner +13

We sketch how developers of frontier AI systems could construct a structured rationale -- a 'safety case' -- that an AI system is unlikely to cause catastrophic outcomes through sc…

◍wovepaper

Papers, researchers and institutions, woven together.

Explore
  • Search
  • Researchers
  • Institutions
Account
  • Library
  • Chat
Data
  • arXiv.org
  • Semantic Scholar
  • OpenAlex
  • Latest RSS
AboutContactPrivacyDevelopersllms.txtopenapi.json
Not affiliated with arXiv. Researcher data from Semantic Scholar (ODC-BY) and OpenAlex.