任务类型 | 数据集名称 | 原始数据数量 | Leaderboard 采样数量 |
---|---|---|---|
qa | nq | 3,610 | 1,000 |
qa | TriviaQA | 11,313 | 1,000 |
qa | popqa | 14,267 | 1,000 |
qa | AmbigQA | 2,002 | 1,000 |
qa | MarcoQA | 101,093 ; 55,636(过滤无答案版本) | 1,000(基于过滤后的) |
qa | WebQuestions | 2,032 | 1,000 |
Multi-hop qa | hotpotqa | 7,405 | 1,000 |
Multi-hop qa | 2WikiMultiHopQA | 12,576 | 1,000 |
Multi-hop qa | Musique | 2,417 | 1,000 |
Multi-hop qa | bamboogle | 125 | 125(未处理) |
Multi-hop qa | strategy-qa | 2,290 | 1,000 |
Multiple-choice | ARC | 3,548 ;(选项为大写字母A-E,其中E选项为1条) | 1,000 |
Multiple-choice | mmlu | 14,042 ;(选项为大写字母A-D) | 1,000 |
Long-form QA | ASQA | 948 | 948(未处理) |
fact-verification | FEVER | 13,332 ;(只保留support和refuse标签) | 1,000 |
dialogue | WoW | 3,054 | 1,000 |
slot-filling | T-REx | 5,000 | 1,000 |
语料库名称 | 文档数量 |
---|---|
wiki2018 | 21,015,324 |
wiki2024 | 即将上线 |