MedHallBench is a comprehensive benchmark framework designed for evaluating and mitigating hallucinations in Multimodal Large Language Models (MLLMs).

Authors

• Person: Not available Organization: arXiv
  [PDF] arXiv:2412.18947v4 [cs.CL] 28 Mar 2025

Sources

• [PDF] arXiv:2412.18947v4 [cs.CL] 28 Mar 2025 arxiv.org arXiv via serper

Referenced by nodes (2)

• hallucination concept
• Multimodal Large Language Models concept