LLM Unlearning; Preference Optimization; Unlearning Robustness

1 paper across 1 session

Poster Session 5

Friday, December 5, 2025 · 11:00 AM → 2:00 PM

Elastic Robust Unlearning of Specific Knowledge in Large Language Models

#3411 · Yize Sui, Jing Ren, Wenjing Yang, Ruochun Jin, Liyang Xu, Xiyao Liu, J Wang

A novel LLM unlearning optimization framework, namely Elastic Robust Unlearning (ERU), to efficiently and robustly remove specific knowledge from LLMs.