Kwan Ho Ryan Chan

PhD student@University of Pennsylvania·美国·OpenReview

研究方向

interpretable machine learning · explainable artificial intelligence · deep learning · generative ai · biomedical machine learning · large language models

7.3

Conformal Information Pursuit for Interactively Guiding Large Language Models

NeurIPS 2025Poster

一作

6.4

SECA: Semantically Equivalent and Coherent Attacks for Eliciting LLM Hallucinations

NeurIPS 2025Poster

6.0

Do LLMs ``know'' internally when they follow instructions?

ICLR 2025Poster

2.5

KDA: A Knowledge-Distilled Attacker for Scalable LLM Red Teaming

ICLR 2025Withdrawn

二作

5.8

Bootstrapping Variational Information Pursuit with Large Language and Vision Models for Interpretable Image Classification

ICLR 2024Poster

二作

5.5

PaCE: Parsimonious Concept Engineering for Large Language Models

合作者 (18)