dwb2023/gdelt-rag-evaluation-inputs
收藏Hugging Face2025-10-20 更新2025-10-25 收录
下载链接:
https://hf-mirror.com/datasets/dwb2023/gdelt-rag-evaluation-inputs
下载链接
链接失效反馈官方服务:
资源简介:
GDELT RAG评估数据集包含来自5种不同检索策略的RAGAS评估输入数据集,这些策略在GDELT RAG系统上进行了测试。每个策略都在相同的黄金测试集的12个问题上进行了评估,提供了检索性能的直接比较。数据集包含大约1,400多条评估记录,涵盖了基准、朴素、BM25、集成和Cohere重排等检索策略。
The GDELT RAG Evaluation Datasets contain consolidated RAGAS evaluation input datasets from 5 different retrieval strategies tested on the GDELT (Global Database of Events, Language, and Tone) RAG system. Each strategy was evaluated on the same golden testset of 12 questions, providing a direct comparison of retrieval performance. The dataset includes ~1,400+ evaluation records across baseline, naive, BM25, ensemble, and cohere_rerank retrieval strategies.
提供机构:
dwb2023



