Yunjun Gao

Papers on Lattice

Total citations

Topics

Publication activitypapers/week, last 8 weeks

Research focus

Constitutional AI & AI Ethics (1)Natural Language Processing (1)Red-Teaming & Adversarial Robustness (1)

Frequent co-authors

Ce Fang (1)Zhikun Zhang (1)Min Chen (1)Qing Liu (1)

Papers (1)

Feb 22, 2026

Ce Fang +53w ago·also NJU

KUDA: Knowledge Unlearning by Deviating Representation for Large Language Models

LLMs can selectively forget specific knowledge without sacrificing overall performance, thanks to a new representation-deviation technique that precisely targets and disrupts unwanted associations.

Ce Fang, Zhikun Zhang, Min Chen +3

Constitutional AI & AI Ethics Natural Language Processing Red-Teaming & Adversarial Robustness

Search

Yunjun Gao

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (1)