← Search

Hans Hao-Hsun Hsu

2 accepted papers

2025

Do LLMs Really Forget? Evaluating Unlearning with Knowledge Correlation and Confidence Awareness

NeurIPS 2025poster

Machine unlearning techniques aim to mitigate unintended memorization in large language models (LLMs). However, existing approaches predominantly focus on the explicit removal of isolated facts, often overlooking latent inferential dependencies and the non-deterministic nature of knowledge within LL…

Cited by 0SourceScholar
2022

What Makes Graph Neural Networks Miscalibrated?

NeurIPS 2022accept

Given the importance of getting calibrated predictions and reliable uncertainty estimations, various post-hoc calibration methods have been developed for neural networks on standard multi-class classification tasks. However, these methods are not well suited for calibrating graph neural networks (GN…