Liao et al. developed a benchmark that reformulates USMLE questions into interactive consultations, requiring Large Language Models to proactively elicit missing patient information.

Authors

• Person: Not available Organization: arXiv
  A Comprehensive Benchmark and Evaluation Framework for Multi ...

Sources

• A Comprehensive Benchmark and Evaluation Framework for Multi ... arxiv.org arXiv via serper

Referenced by nodes (1)

• Large Language Models concept