Quality of Large Language Model Responses to Radiation Oncology Patient Care Questions
Description of Resource
This publications outlines a comprehensive evaluation approach to determine an LLM’s quality of responses to radiation oncology patient care questions using both domain-specific expertise and domain-agnostic metrics. Domain-specific expertise involves evaluating LLM-generated responses through human expert assessments, augmented with Likert scales, while domain-agnostic evaluation utilizes computational quantitative techniques to assess the LLM-generated responses.
Type of Resource
Research Article, Use Case Example, Application/Tool