4 papers
Shape it Up! Restoring LLM Safety during Finetuning
ShengYun Peng, Pin-Yu Chen, Jianfeng Chi +2
Finetuning large language models (LLMs) enables user-specific customization but introduces critical safety risks: even a few harmful examples can compromise safety alignment. A com…
Probing LLM Hallucination from Within: Perturbation-Driven Approach via Internal Knowledge
Seongmin Lee, Hsiang Hsu, Chun-Fu Chen +1
LLM hallucination, where unfaithful text is generated, presents a critical challenge for LLMs' practical applications. Current detection methods often resort to external knowledge,…
Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety
Seongmin Lee, Aeree Cho, Grace C. Kim +3
As large language models (LLMs) see wider real-world use, understanding and mitigating their unsafe behaviors is critical. Interpretation techniques can reveal causes of unsafe out…
Effective Guidance for Model Attention with Simple Yes-no Annotations
Seongmin Lee, Ali Payani, Duen Horng Chau
Modern deep learning models often make predictions by focusing on irrelevant areas, leading to biased performance and limited generalization. Existing methods aimed at rectifying m…