Katherine Metcalf

Researcher@Apple·美国·OpenReview

研究方向

human in the loop learning · human robot interaction · reinforcement learning from human feedback · RLHF · preference learning · alignment · PbRL · preference-based reinforcement learning

4.0

Normalized Rewards for Preference Learning

ICLR 2026Rejected

通讯

2.5

Evaluating the Evaluators: Investigating LLM Judges for Personalized Writing Style Assessment

ICLR 2026Withdrawn

通讯

6.5

Investigating Intersectional Bias in Large Language Models using Confidence Disparities in Coreference Resolution

COLM 2025Poster

5.5

Aligning LLMs by Predicting Preferences from User Writing Samples

ICML 2025Poster

通讯

5.5

Is Your Model Fairly Certain? Uncertainty-Aware Fairness Evaluation for LLMs

ICML 2025Poster

5.5

PREDICT: Preference Reasoning by Evaluating Decomposed preferences Inferred from Candidate Trajectories

ICLR 2025Rejected

通讯

3.0

Uncovering Intersectional Stereotypes in Humans and Large Language Models

合作者 (19)

Stéphane Aroca-Ouellette

2 篇