CRASS
收藏DataCite Commons2026-01-07 更新2025-04-16 收录
下载链接：
https://service.tib.eu/ldmservice/dataset/84e1ad19-4bf6-46a4-8e31-4238d5dd7b59
下载链接
链接失效反馈官方服务：
资源简介：
The CRASS dataset is a novel basis to test reasoning and natural language understanding of large language models. It consists of 274 high-quality premise-counterfactual tuples, where each tuple contains a premise, a counterfactual conditional, and a set of potential effects as distractors.
提供机构：
TIB
创建时间：
2025-01-03
