LAMBADA multilingual (OpenAI MT)

lm-eval group of OpenAI-format LAMBADA last-word tests in English and machine-translated German, Spanish, French and Italian (5,153 passages each).

Also known as: lambada_openai_mt, lambada_mt

unassessed

This page is a discovery lead. Nobody has yet assessed it against the catalogue contract, so it carries no disposition. Absence of evidence here is not evidence of staleness.
Categoryreasoning
Subcategorymultilingual last-word prediction on machine-translated LAMBADA
Page statusactive
Metricaccuracy (next-word exact match); perplexity also reported
Directionhigher_is_better
Unit%
Dataset size25765
Dataset licenceMIT (Hugging Face cardData); README Licensing section cites Modified MIT (OpenAI GPT-2)
PublisherEleutherAI (harness group and Hugging Face mirror); original LAMBADA, University of Trento CIMeC and University of Amsterdam

What it measures

lambada_multilingual is EleutherAI's lm-evaluation-harness group over five OpenAI-format LAMBADA cloze sets. Each item is a narrative passage whose last word is withheld; the model must assign higher likelihood to that word than to alternatives, using discourse beyond the final sentence. Four configs are machine translations of the English OpenAI test split into German, Spanish, French and Italian. The fifth, English, loads Hugging Face config `en` rather than the `default` config used by lambada_openai. Text only.

Task format

Causal language-model cloze scored as loglikelihood, not free generation. Prompt is the passage minus the last whitespace token; the target is a leading space plus that token. Runnable task names are lambada_openai_mt_{en,de,es,fr,it}.

Models reporting this benchmark

No model card in ModelSpec reports this benchmark yet.

Data

This page as JSON · Edit on GitHub