Anna Hedström

~Anna_Hedström1

4

论文总数

2.0

年均投稿

6.3

平均评分

接收情况3/4

会议分布

NeurIPS

2

ICML

1

ICLR

1

发表论文 (4 篇)

20253 篇

To Steer or Not to Steer? Mechanistic Error Reduction with Abstention for Language Models

ICML 2025Poster

Benchmarking XAI Explanations with Human-Aligned Evaluations

ICLR 2025Rejected

Capturing Polysemanticity with PRISM: A Multi-Concept Feature Description Framework

NeurIPS 2025Poster

20241 篇

CoSy: Evaluating Textual Explanations of Neurons

NeurIPS 2024Poster

合作者 (20)

Kirill Bykov2 篇

Laura Kopf2 篇

Marina MC Höhne2 篇

Philine Lou Bommer2 篇

Andrea Passerini1 篇

Baptiste Caramiaux1 篇

Eloïse Berthier1 篇