影响力指数

13.63/100

超过 41.9%

全站排名 #37,393

发表论文3 篇

平均评分5.0

年均产出1.5 篇/年

Erik Miehling

Research Scientist@IBM Research·爱尔兰·OpenReview

研究方向

Fairness · Reinforcement learning · Game theory · Stochastic control

Interpreting LLM-as-a-Judge Policies via Verifiable Global Explanations

ICLR 2026Rejected

Programming Refusal with Conditional Activation Steering

ICLR 2025Spotlight

CELL your Model: Contrastive Explanations for Large Language Models

ICLR 2025Withdrawn

合作者 (12)

Amit Dhurandhar

Karthikeyan Natesan Ramamurthy

Manish Nagireddy

Elizabeth M. Daly