5 papers
Generalizable Lifelong Model Editing via Preference Optimization
Dahyun Jung, Suhyune Son, Heuiseok Lim
Knowledge editing enables rapid updates of specific factual knowledge in large language models (LLMs) without full retraining. However, more realistic scenarios call for a lifelong…
Towards Scalable Lifelong Knowledge Editing with Selective Knowledge Suppression
Dahyun Jung, Jaewook Lee, Heuiseok Lim
Large language models (LLMs) require frequent knowledge updates to reflect changing facts and mitigate hallucinations. To meet this demand, lifelong knowledge editing has emerged a…
FLEX: A Benchmark for Evaluating Robustness of Fairness in Large Language Models
Dahyun Jung, Seungyoon Lee, Hyeonseok Moon +2
Recent advancements in Large Language Models (LLMs) have significantly enhanced interactions between users and models. These advancements concurrently underscore the need for rigor…
CoME: An Unlearning-based Approach to Conflict-free Model Editing
Dahyun Jung, Jaehyung Seo, Jaewook Lee +2
Large language models (LLMs) often retain outdated or incorrect information from pre-training, which undermines their reliability. While model editing methods have been developed t…
Alternative Speech: Complementary Method to Counter-Narrative for Better Discourse
Seungyoon Lee, Dahyun Jung, Chanjun Park +2
We introduce the concept of "Alternative Speech" as a new way to directly combat hate speech and complement the limitations of counter-narrative. An alternative speech provides pra…