2 papers
cs.SE2025
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…
cs.CV2025
Captured by Captions: On Memorization and its Mitigation in CLIP Models
Wenhao Wang, Adam Dziedzic, Grace C. Kim +2
Multi-modal models, such as CLIP, have demonstrated strong performance in aligning visual and textual representations, excelling in tasks like image retrieval and zero-shot classif…