QASPER-cut

OpenCompass QASPER variant that keeps extractive-span questions and feeds the paper text from the first gold evidence offset onward.

Also known as: qaspercut, QASPERCUT

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.
Categorylong-context
SubcategoryOpenCompass QASPER extractive QA with the paper cut at first evidence
Page statusunknown
MetricTriviaQA token F1 (TriviaQAEvaluator)
Directionhigher_is_better
Unit%
Dataset licenceCC-BY-4.0
PublisherAllen Institute for AI (QASPER data); OpenCompass (cut wrap)

What it measures

qaspercut is not a second copy of [qasper](qasper.md). It uses the same QASPER validation JSON, but it drops every question that has no extractive span and it truncates each paper. The loader finds the earliest gold evidence string in the concatenated full text, then passes only the suffix from that offset as the prompt context. The model still has to read a long remainder of the paper, but it is handed a cut that starts at (or near) a human-highlighted clue instead of the title page.

Task format

Zero-shot generation on the QASPER dev split. Prompt is evidence suffix, then "Answer these questions: Q: {question}? A:". Gold is the list of extractive spans. Evaluator is OpenCompass TriviaQAEvaluator.

Models reporting this benchmark

No model card in ModelSpec reports this benchmark yet.

Data

This page as JSON · Edit on GitHub