English

DocLens: Multi-aspect Fine-grained Evaluation for Medical Text Generation

Computation and Language 2024-10-04 v3

Abstract

Medical text generation aims to assist with administrative work and highlight salient information to support decision-making. To reflect the specific requirements of medical text, in this paper, we propose a set of metrics to evaluate the completeness, conciseness, and attribution of the generated text at a fine-grained level. The metrics can be computed by various types of evaluators including instruction-following (both proprietary and open-source) and supervised entailment models. We demonstrate the effectiveness of the resulting framework, DocLens, with three evaluators on three tasks: clinical note generation, radiology report summarization, and patient question summarization. A comprehensive human study shows that DocLens exhibits substantially higher agreement with the judgments of medical experts than existing metrics. The results also highlight the need to improve open-source evaluators and suggest potential directions.

Keywords

Cite

@article{arxiv.2311.09581,
  title  = {DocLens: Multi-aspect Fine-grained Evaluation for Medical Text Generation},
  author = {Yiqing Xie and Sheng Zhang and Hao Cheng and Pengfei Liu and Zelalem Gero and Cliff Wong and Tristan Naumann and Hoifung Poon and Carolyn Rose},
  journal= {arXiv preprint arXiv:2311.09581},
  year   = {2024}
}

Comments

ACL Camera Ready Version

R2 v1 2026-06-28T13:22:57.939Z