ttomov/ambigqa_star
收藏Hugging Face2025-11-07 更新2025-11-15 收录
下载链接：
https://hf-mirror.com/datasets/ttomov/ambigqa_star
下载链接
链接失效反馈官方服务：
资源简介：
AmbigQA*是一个用于评估大型语言模型在非零样本不确定性下不确定性量化（UQ）的基准数据集。它包含具有多个正确答案的模糊问题，并提供了基于大规模语料库共现统计的答案分布。
AmbigQA* is a benchmark dataset for evaluating uncertainty quantification (UQ) in large language models (LLMs) under non-zero aleatoric uncertainty, containing ambiguous questions with multiple correct answers and providing ground-truth answer distributions based on large-scale corpus co-occurrence statistics.
提供机构：
ttomov
