Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
PEPPER: Perception-Guided Perturbation for Robust Backdoor Defense in Text-to-Image Diffusion Models
Oscar Chew, Po-Yi Lu, Jayden Lin +2
Recent studies show that text to image (T2I) diffusion models are vulnerable to backdoor attacks, where a trigger in the input prompt can steer generation toward harmful or uninten…
cs.CL2025
The Role of Exploration Modules in Small Language Models for Knowledge Graph Question Answering
Yi-Jie Cheng, Oscar Chew, Yun-Nung Chen
Integrating knowledge graphs (KGs) into the reasoning processes of large language models (LLMs) has emerged as a promising approach to mitigate hallucination. However, existing wor…