up-to-date curated list of state-of-the-art Large vision language models hallucinations research work, papers & resources

[ICLR 2025] MLLM can see? Dynamic Correction Decoding for Hallucination Mitigation

A novel alignment framework that leverages image retrieval to mitigate hallucinations in Vision Language Models.

PAINT (Paying Attention to INformed Tokens) is a plug-and-play framework that intervenes in the self-attention of the LLM and selectively boost the visual attention informed tokens to mitigate hallucination of Vision Language Models

Fully automated LLM evaluator

[ICLR 2025] Data-Augmented Phrase-Level Alignment for Mitigating Object Hallucination

Detecting Hallucinations in LLMs