影响力指数
论文质量、代表作、近期表现、广度与样本量置信度综合计算
62.36/100
前 4.2%
全站排名 #2,688
发表论文10 篇
平均评分
年均产出3.3 篇/年
Owain Evans
研究方向
AI safety · large language models · cognitive science · language models · creative AI
11
Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs
ICML 2025Oral
通讯28
Tell me about yourself: LLMs are aware of their learned behaviors
ICLR 2025Spotlight
通讯29
Looking Inward: Language Models Can Learn About Themselves by Introspection
ICLR 2025Poster
通讯6
The Two-Hop Curse: LLMs trained on A→B, B→C fail to learn A→C
ICLR 2025Rejected
三作