Datasets
Dataset
MultiQ
by caro-holt
Dataset Card for MultiQ This is the dataset corresponding to the paper "Evaluating the Elementary Multilingual Capabilities of Large Language Models with MultiQ". It is a silver standard benchmark that can be used to evaluate the basic multilingual capabili…
CC-BY-4.0question-answering 234 810K < n < 100K rows
published 2 Mar 2024
Preview
First 5 rows of default / train, from the Hugging Face dataset viewer.
| id | language | prompt | domain |
|---|---|---|---|
| gpt-1 | ee | Nukae nye atike si wozãna tsɔ wɔa tsi? | chemistry |
| gpt-2 | ee | Nukae nye tsi ƒe ƒoƒo le atsiaƒu ƒe kɔkɔme? | chemistry |
| gpt-3 | ee | Nukawoe nye nuwo ƒe nɔnɔme etɔ̃awo? | chemistry |
| gpt-4 | ee | Nukae dzɔna ɖe tsi dzi ne efa ale gbegbe? | chemistry |
| gpt-5 | ee | Nukae nye nuwo ƒe akpa suetɔ kekeake? | chemistry |
Cite this
CC-BY-4.0textCite
Tags
task_categories:question-answeringlanguage:tllanguage:smlanguage:mklanguage:gulanguage:filanguage:mnlanguage:bmlanguage:talanguage:urlanguage:hylanguage:nllanguage:tklanguage:enlanguage:bglanguage:gdlanguage:ptlanguage:kolanguage:galanguage:eulanguage:svlanguage:bslanguage:colanguage:frlanguage:gnlanguage:rolanguage:itlanguage:dvlanguage:kulanguage:aklanguage:eolanguage:zulanguage:idlanguage:telanguage:sllanguage:lvlanguage:palanguage:rulanguage:silanguage:ee