Identify, Isolate, and Purge: Mitigating Hallucinations in LVLMs via Self-Evolving Distillation
Published in ACM MM 2025, Oral, CCF A, 2025
This work studies hallucination mitigation in large vision-language models by separating hallucination-prone knowledge and purging it through self-evolving distillation.
Recommended citation: Li W, et al. Identify, Isolate, and Purge: Mitigating Hallucinations in LVLMs via Self-Evolving Distillation. ACM International Conference on Multimedia (ACM MM), 2025. Oral, CCF A. First author.