Mengdi Huai
Position
- Assistant Professor
Recent Publications
- Towards Benchmarking Privacy Vulnerabilities in Selective Forgetting with Large Language Models. AAAI 2026: 37839-37848
- Quantifying and Understanding Uncertainty in Large Reasoning Models. ACL (1) 2026: 32741-32754
- Rethinking Unlearnable Examples in Machine Unlearning. PAKDD (2) 2026: 40-53
- Uncertainty-Aware Language Guidance for Concept Bottleneck Models. PAKDD (4) 2026: 386-398
- Selective Forgetting for Large Reasoning Models. PAKDD (4) 2026: 412-423