Yihuai Hong@ACL 2024
@yihuaih91773
CS Undergraduate @SCUT prev RA in @UCL.
Mechanistic Interpretability, LLM Safety, Post-training .
Looking for 2025 PhD opportunities and Research Internship:)
ID: 1676191639637749760
https://yihuaihong.github.io/ 04-07-2023 11:30:17
10 Tweet
164 Takipçi
361 Takip Edilen
🚀The first-ever parametric LLM Unlearning Benchmark! We find current unlearning only modify model’s behavior without truly erasing encoded knowledge in parameters, presenting ConceptVectors Benchmark, with each vector strongly tied to a specific concept.🔗yihuaihong.github.io/ConceptVectors…
