Lucas Dixon

~Lucas_Dixon1

3

论文总数

1.5

年均投稿

6.6

平均评分

接收情况2/3

会议分布

ICLR

2

NeurIPS

1

发表论文 (3 篇)

20251 篇

Scalable Influence and Fact Tracing for Large Language Model Pretraining

ICLR 2025Poster

20242 篇

Interpretability Illusions in the Generalization of Simplified Models

ICLR 2024Rejected

Who's asking? User personas and the mechanics of latent misalignment

NeurIPS 2024Spotlight

合作者 (12)

Asma Ghandeharioun2 篇

Emily Reif1 篇

Marius Guerard1 篇

Michael A. Lepori1 篇

Dheeraj Rajagopal1 篇

Ian Tenney1 篇

Tolga Bolukbasi1 篇