MS_MARCO Benchmark

What is MS_MARCO?

MS MARCO comprises of 1,010,916 anonymized questions—sampled from Bing’s search query logs—each with a human generated answer and 182,669 completely human…

Released

2018-10-31

Evaluates

知识, Knowledge, 大语言模型, LLM, 检索能力, Retrieval, 不支持, Unsupported

Openness

unknown

Importer

OpenCompass Hub

Reported scores

0

Source provenance

• Original evidence https://hub.opencompass.org.cn/dataset-detail/MS_MARCO

MS_MARCO paper and code

• Paper https://arxiv.org/pdf/1611.09268
• Code https://github.com/microsoft/MSMARCO-Question-Answering

Which sources cite MS_MARCO?

• MS_MARCO

Related 知识, Knowledge, 大语言模型, LLM, 检索能力, Retrieval, 不支持, Unsupported benchmarks

• A-Bench
• A-OKVQA
• AbsPyramid
• ActionAtlas
• Ada-LEval
• AECBench
• AFQMC
• AgentBoard