Picture for Xinyang Lu

Xinyang Lu

Global-to-Local Support Spectrums for Language Model Explainability

Add code
Aug 12, 2024
Viaarxiv icon

TRACE: TRansformer-based Attribution using Contrastive Embeddings in LLMs

Add code
Jul 06, 2024
Viaarxiv icon

On Newton's Method to Unlearn Neural Networks

Add code
Jun 20, 2024
Viaarxiv icon

WASA: WAtermark-based Source Attribution for Large Language Model-Generated Data

Add code
Oct 01, 2023
Viaarxiv icon

Action and Trajectory Planning for Urban Autonomous Driving with Hierarchical Reinforcement Learning

Add code
Jun 28, 2023
Viaarxiv icon

Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs

Add code
Jun 22, 2023
Viaarxiv icon