A training-free, head-level intervention framework for Large Vision-Language Models identifies critical hallucination heads across causal pathways and applies targeted corrections for yes/no, multiple-choice, and open-ended question-answer formats.

Authors

• Person: Not available Organization: GitHub
  EdinburghNLP/awesome-hallucination-detection - GitHub

Sources

• EdinburghNLP/awesome-hallucination-detection - GitHub github.com GitHub via serper

Referenced by nodes (1)

• Large Vision-Language Models concept