Youyang Qu

Researcher, CSIRO

1 paper at NeurIPS 2025

OpenReview· Semantic Scholar· Google Scholar

Poster Session 3

1 paper

Thursday, December 4, 2025 · 11:00 AM → 2:00 PM

Exhibit Hall C,D,E

Wisdom is Knowing What not to Say: Hallucination-Free LLMs Unlearning via Attention Shifting

#1401 · Chenchen Tan, Youyang Qu, Xinghao Li, Hui Zhang, Shujie Cui, Cunjian Chen, Longxiang Gao

We propose an attention-shifting-based unlearning method for large language models, which enables precise removal of target knowledge while preserving utility and mitigating hallucinations.