Patient-specific rubric-based evaluation of large language models across longitudinal cancer care

Wei-Wei Zhang, Pengkai Wang, Yan Li, Zhijie Sang, Guan-Qun Zhou et al.|October 26, 2026arXiv

Key Takeaway

LLMs need phase-specific evaluation and safeguards for medical AI—strong performance on one clinical task doesn't guarantee reliability across the full patient journey, and the types of errors models make shift dramatically depending on the care stage.

Summary

This paper introduces NPC-RubricBench, a benchmark for evaluating how well large language models handle cancer care across multiple treatment phases rather than single encounters.

evaluation safety applications

Key Terms

rubric-based-evaluation phase-aware-benchmark longitudinal-evaluation decision-omission evidence-faithfulness