Med EvalsJin et al. / EMNLP-IJCNLP 2019
PubMedQA: A Dataset for Biomedical Research Question Answering ↗
Original benchmark construction, split, settings and baseline results.
Version: November 2019
Evidence locator: §3; Tables 1, 4–5
aclanthology.orgEvidence / original sources
A claim should lead somewhere.
Follow the references behind Med Evals. Each entry explains its role, links to the original publication, and identifies the guides that use it.
Content updated September 28, 2026. Inclusion does not imply endorsement.
PubMedQA authors
PubMedQA official data and evaluation repository ↗
Release organization, split procedure and prediction format.
Version: Accessed 2026-09-28
Evidence locator: README; data; preprocess
github.comPubMedQA authors
PubMedQA evaluation.py ↗
Exact test-key check, accuracy and macro-F1 implementation.
Version: Accessed 2026-09-28
Evidence locator: evaluation.py
github.comPubMedQA authors
PubMedQA repository license ↗
MIT repository license; does not independently clear underlying article rights.
Version: 2019
Evidence locator: LICENSE
github.comUsed inPubMedQA dossier →
Nentidis et al. / BioASQ organizers
Overview of BioASQ Tasks 12b and Synergy12 in CLEF2024 ↗
Edition-specific stages and batch counts; training total differs between text and Table 1.
Version: CLEF 2024
Evidence locator: §2.1; Table 1
www.iit.demokritos.grBioASQ organizers
BioASQ task b datasets ↗
Official edition catalog lists 5,046 questions for Training 12b and requires registration for downloading.
Version: Accessed 2026-09-28
Evidence locator: Task b dataset table
participants-area.bioasq.orgBioASQ organizers
Twelfth Challenge Winners ↗
Official phase-specific ranking rules; no scores from different answer types are interchangeable.
Version: 2024 challenge
Evidence locator: Task 12b selection strategies
taskb.bioasq.org