OLAPH / MedLFQA

lm-eval wrap of MedLFQA: English biomedical long answers scored with BLEU, ROUGE, BERTScore and BLEURT on a 10% slice.

Also known as: MedLFQA, dmis-lab/MedLFQA, olaph_perplexity

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.
Categorydomain
Subcategorybiomedical long-form question answering
Page statusactive
MetricBLEU, ROUGE-1/2/L, BERTScore, BLEURT (nanmean)
Directionhigher_is_better
Dataset size4948
Dataset licenceCC-BY-4.0
PublisherKorea University DMIS Lab (with Upstage AI and AIGEN Sciences)

What it measures

olaph, as this id, is EleutherAI's generate-until task on dmis-lab/MedLFQA. The model reads an English patient-style biomedical question and must write a long answer. Jeong et al. built MedLFQA so they could score factual claims (Must Have / Nice to Have statements) while training the OLAPH preference loop. The harness task does not score those claims. It compares the free-form answer to Free_form_answer with n-gram and embedding overlap. English text only. This is not [HealthBench](healthbench.md).

Task format

Open-ended generation. YAML description tells the model it is a healthcare assistant and to answer concisely without omitting relevant information. Stops at a blank line. training/validation/test splits all point at the Hub test split. process_docs keeps the first 10% of rows (code uses 0.1; the comment says 1%). Sister task olaph_perplexity uses loglikelihood_rolling on the same slice.

Models reporting this benchmark

No model card in ModelSpec reports this benchmark yet.

Data

This page as JSON · Edit on GitHub