Logo Lanfrica
  • Accueil
  • Atlas
  • Analyses
  • Documentation
  • Sign in

© 2026 Lanfrica. Tous droits réservés. Tous les droits d'auteur des ressources affichées sur le site Web Lanfrica appartiennent aux détenteurs de droits d'auteur d'origine, sauf indication contraire explicite.

MLAIRE-BELEBELE

Domaine:

natural language processing

Type de record:

dataset
Créateur:
ano
Hôte:
Belebele reformatted for language-aware retrieval evaluation. 488 underlying passages, each available in 122 languages (joined globally by the original link field). Relevance is encoded by group_id matching. This repository is part of the MLAIRE benchmark, submitted anonymously to the NeurIPS 2026 Evaluations & Datasets Track. Authors and affiliations are withheld for double-blind review. Default top-k

Visit

huggingface.co

Tasks

information retrieval

Languages

AfrikaansAmharicArabic, Egyptian SpokenArabic, Moroccan SpokenBamanankanChichewaDholuoFulfulde, NigerianGandaHausa+19

Tags

retrievalmultilinguallanguage-aware-irmlaire

Licenses

cc-by-sa-4.0

Similaires

BelebeleBelebele2M Belebele SpeechThe Belebele Benchmark: a Parallel Reading Comprehension Dataset in 122 Language Variants

Belebele

The Belebele Benchmark for Massively Multilingual NLU Evaluation

Belebele

The Belebele Benchmark for Massively Multilingual NLU Evaluation

2M Belebele Speech

We introduce 2M-Belebele as the first highly multilingual speech and American Sign Language (ASL) co

The Belebele Benchmark: a Parallel Reading Comprehension Dataset in 122 Language Variants

We present Belebele, a multiple-choice machine reading comprehension (MRC) dataset spanning 122 lang