SQuAD completion (Based / lm-eval)

Based and lm-eval rewrite 2,984 SQuAD validation items as next-token completions, scored by case-insensitive contains.

Also known as: based-squad, hazyresearch/based-squad

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
SubcategorySQuAD passages rewritten so the gold span is the last tokens of a statement
Page statusunknown
Metriccontains
Directionhigher_is_better
Dataset size2984
PublisherHazy Research (Stanford); EleutherAI lm-evaluation-harness

What it measures

squad_completion is a recall-style reading task, not span extraction and not SQuAD 2.0 abstention. A passage is followed by a statement that ends with the answer. The model must continue the statement so the generation contains that gold span. Hazy Research built the items for the BASED paper by asking GPT-4 to rewrite question-answer pairs as statements that end with the answer, then dropping rewrites that failed that check. English text. Zero-shot generation.

Task format

generate_until: prompt is doc["text"] with surrounding whitespace stripped; gold is doc["value"] stripped. Decoding stops at a newline, max_gen_toks 48. Metric is contains: case-insensitive regex search of the gold string inside the continuation. lm-eval VERSION 1.

Models reporting this benchmark

No model card in ModelSpec reports this benchmark yet.

Data

This page as JSON · Edit on GitHub