SQuAD 2.0 (OpenCompass squad20)

OpenCompass's squad20 task runs the SQuAD 2.0 dev set, prompting a model to extract an answer span or say "impossible to answer" for adversarial unanswerable questions.

Also known as: SQuAD2.0

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
Subcategoryextractive reading comprehension with unanswerable questions, as implemented by OpenCompass's squad20 config
Page statussaturated
MetricSQuAD20Evaluator (Exact Match / F1 against reference answers, with a literal 'impossible to answer' string scored against unanswerable questions)
Directionhigher_is_better
Unit%
Dataset size11873
Dataset licenceCC BY-SA 4.0
PublisherStanford University (original dataset); OpenCompass (open-compass) maintains this harness implementation

What it measures

This is the OpenCompass harness implementation of SQuAD 2.0 (id `squad20`, config abbreviation `squad2.0`): given a Wikipedia passage and a question, the model must either return the answer text found in the passage or state that the question is impossible to answer, since over 50,000 of SQuAD 2.0's questions are adversarially written to closely resemble answerable ones while having no supported answer in the passage. See [SQuAD](squad.md) for the full history and dataset detail shared by both SQuAD 1.1 and 2.0; this page documents the specific harness variant that model cards in this repository score under the id `squad20`.

Task format

OpenCompass reads `dev-v2.0.json` locally and prompts: "According to the above passage, answer the following question. If it is impossible to answer according to the passage, answer 'impossible to answer'", followed by the question, with generation capped at 50 tokens.

Models reporting this benchmark

No model card in ModelSpec reports this benchmark yet.

Data

This page as JSON · Edit on GitHub