datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
sam2-vit-bsam2-vit-sodia-minimind-dataestsASTRA-QA
ASTRA-QA: A Benchmark for Abstract Question Answering over Documents
ASTRA-QA, short for AbSTRAct Question Answering over documents, is a dataset and benchmark for document-level, synthesis-heavy question answering in retrieval-augmented generation systems.
It evaluates whether a system can read long documents, organize evidence, and produce grounded abstractive answers with reference-based assessment, rather than only retrieve short facts.
Dataset Summary
869… See the full description on the dataset page: https://huggingface.co/datasets/sam234990/ASTRA-QA.article_aljazeeratest_imageus-finance-sector-datasetsam2