α
Research
Alpha Leak
Conferences
Topics
Top Authors
Rankings
Browse All
EN
中
Home
/
Authors
/
Owain Evans
Owain Evans
2
Papers
150
Total Citations
2
Affiliations
Affiliations
Truthful AI
UC Berkeley
Papers (2)
Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs
ICML 2025
110
citations
Looking Inward: Language Models Can Learn About Themselves by Introspection
ICLR 2025
arXiv
40
citations