Do quality filters pull benchmark questions into pretraining corpora? Injects MMLU, GSM8K, GPQA, ARC, HellaSwag, PIQA and TruthfulQA items into a corpus and ranks them with six quality classifiers, including DCLM, FineWeb-Edu and Gaperon.
python nlp data-filtering data-curation data-contamination gsm8k mmlu llm-evaluation fineweb dataset-quality pretraining-data llm-benchmark benchmark-contamination quality-filter
-
Updated
Aug 19, 2026 - Python