Can I read Hallucination in Vision-Language Models on EtoBox?

Hallucination in Vision-Language Models by xu.battle is a document available to read on EtoBox.

What is Hallucination in Vision-Language Models about?

This survey examines hallucinations in Large Vision-Language Models (LVLMs), focusing on the discrepancies between visual content and generated textual descriptions. It categorizes hallucinations into judgment and description types, discusses their causes, and reviews existing mitigation strategies. The document also highlights the challenges in evaluating hallucinations and suggests future research directions to enhance the reliability of LVLMs.

Author

xu.battle

Language

EN