showlab/Awesome-MLLM-Hallucination
A curated list of research papers, surveys, and code resources on hallucination in multimodal large language models.
Not currently ranked — collecting fresh signals.
star history
This repository organizes academic and practical resources focused on hallucination in multimodal large language models (MLLM) or large vision-language models (LVLM). Hallucination here refers to generated text that is nonsensical or unfaithful to the source content, including factual errors or instruction violations. The collection includes a comprehensive 40-page survey with 228 references covering root causes, training-free mitigations, contrastive decoding, and RL-based solutions.
Frequently asked
- What is showlab/Awesome-MLLM-Hallucination?
- A curated list of research papers, surveys, and code resources on hallucination in multimodal large language models.
- Is Awesome-MLLM-Hallucination open source?
- Yes — showlab/Awesome-MLLM-Hallucination is an open-source project tracked on heatdrop.
- How popular is Awesome-MLLM-Hallucination?
- showlab/Awesome-MLLM-Hallucination has 1k stars on GitHub.
- Where can I find Awesome-MLLM-Hallucination?
- showlab/Awesome-MLLM-Hallucination is on GitHub at https://github.com/showlab/Awesome-MLLM-Hallucination.