The paper "Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key" by Yang et al. (2025) argues that the use of on-policy data is critical for mitigating hallucinations in large vision-language models when using direct preference optimization.

Authors

• Person: Not available Organization: GitHub
  Awesome-Hallucination-Detection-and-Mitigation - GitHub

Sources

• Awesome-Hallucination-Detection-and-Mitigation - GitHub github.com GitHub via serper

Referenced by nodes (3)

• Large Vision-Language Models concept
• hallucination mitigation concept
• Direct Preference Optimization (DPO) concept