Owain Evans
~Owain_Evans1
9
论文总数
4.5
年均投稿
平均评分
接收情况6/9
会议分布
ICLR
7
NeurIPS
1
ICML
1
发表论文 (9 篇)
20254 篇
4
The Two-Hop Curse: LLMs trained on A→B, B→C fail to learn A→C
ICLR 2025Rejected
5
Tell me about yourself: LLMs are aware of their learned behaviors
ICLR 2025Spotlight
4
Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs
ICML 2025Oral
4
Looking Inward: Language Models Can Learn About Themselves by Introspection
ICLR 2025Poster
20245 篇
4
Tell, Don't Show: Internalized Reasoning influences how LLMs generalize
ICLR 2024Rejected
3
Language Models Struggle to Explain Themselves
ICLR 2024Rejected
5
Connecting the Dots: LLMs can Infer and Verbalize Latent Structure from Disparate Training Data
NeurIPS 2024Poster
4
How to Catch an AI Liar: Lie Detection in Black-Box LLMs by Asking Unrelated Questions
ICLR 2024Poster
4
The Reversal Curse: LLMs trained on “A is B” fail to learn “B is A”
ICLR 2024Poster