Unverified50% confidenceFactExact time
Belebele is a multilingual reading comprehension dataset covering 122 languages, with each question accompanied by four candidate passages, commonly used to evaluate the cross-lingual retrieval ability of multilingual embedding models.
1
Sources
50%
Confidence
Long-term
Relevance
11/10/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedA model trained in one of these languages can also improve Belebele performance in other languages, but the improvement is smaller than training directly on the target language.65% similarUnverifiedA study on Bengali idioms used six frozen encoders, 10,359 Bengali idiom items, and eight input conditions to systematically test the reading, transfer, and erasure of cross-lingual concept subspaces.63% similarUnverifiedBitext mining is a classic evaluation task for cross-lingual embeddings: given sentence sets in each of two languages, the system must find, for each sentence, the semantically corresponding translated sentence in the other language.62% similarUnverifiedThe SWORD benchmark covers eight widely used languages to systematically examine models' cross-lingual fact-checking consistency.62% similarUnverifiedWhen the query and document have spelling overlap, the model appears multilingual; only cross-lingual testing (asking in language A and answering in language B) can prove that the model truly has multilingual capability.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1153287API
curl https://kongchang.com/api/v1/knowledge/claims/1153287MCP
get_claim(id=1153287)