Incorporating domain-specific knowledge and introducing a 'not sure' category as one of the answer categories improves precision and F1 scores by up to 38% relative to baselines in the MedHallu benchmark.

Authors

• Person: Not available Organization: arXiv
  [2502.14302] MedHallu: A Comprehensive Benchmark for Detecting ...

Sources

• [2502.14302] MedHallu: A Comprehensive Benchmark for Detecting ... arxiv.org arXiv via serper

Referenced by nodes (3)

• Precision concept
• F1 score concept
• Domain-Specific Knowledge concept