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
46.55/100
前 10.1%
全站排名 #6,498
发表论文5 篇
平均评分
年均产出2.5 篇/年
Katherine Lee
研究方向
datasets · evaluation · language models · copyright · privacy
19
Exploring the limits of strong membership inference attacks on large language models
NeurIPS 2025Poster
20
Recite, Reconstruct, Recollect: Memorization in LMs as a Multifaceted Phenomenon
ICLR 2025Poster
25
Scalable Extraction of Training Data from Aligned, Production Language Models
ICLR 2025Poster
通讯7
Exploring and Mitigating Adversarial Manipulation of Voting-Based Leaderboards
ICML 2025Oral