MedRECT: A Medical Reasoning Benchmark for Error Correction in Clinical Texts
收藏官方服务：
资源简介：
This dataset is evaluation results for the MedRECT benchmark, including model raw responses and predictions for Japanese and English medical error correction tasks. These results correspond to the experiments described in our paper. https://arxiv.org/abs/2511.00421For detailed descriptions, please refer to the README in the GitHub repository. https://github.com/pfnet-research/medrect
提供机构：
Zenodo创建时间：
2025-11-07
