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
14.43/100
超过 44.1%
全站排名 #35,996
发表论文4 篇
平均评分
年均产出2.0 篇/年
Sarah Ball
研究方向
mechanistic interpretability · jailbreaks · large language models
19
On the Impossibility of Separating Intelligence from Judgment: The Computational Intractability of Filtering for AI Alignment
ICLR 2026Poster
一作13
Don't Walk the Line: Boundary Guidance for Filtered Generation
ICLR 2026Rejected
一作5
Towards Understanding the Transferability of Adversarial Suffixes in Large Language Models
ICLR 2026Withdrawn
一作