UKPLab/PeerQA

Code and Data for PeerQA: A Scientific Question Answering Dataset from Peer Reviews, NAACL 2025

46
/ 100
Emerging

This project offers a unique dataset of questions and answers derived from scientific peer reviews. It helps researchers and developers create and evaluate AI systems that can automatically find evidence, identify unanswerable questions, and generate answers based on full academic papers. The primary users are researchers in natural language processing and machine learning working on advanced question-answering systems for scientific texts.

Use this if you are building or testing AI models designed to understand and respond to complex scientific questions within academic papers, particularly those found in peer review contexts.

Not ideal if you need a general-purpose question-answering dataset that isn't focused on scientific documents or the specific structure of peer-review questions.

scientific-research peer-review academic-publishing question-answering natural-language-processing
No Package No Dependents
Maintenance 10 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

12

Forks

4

Language

Python

License

Apache-2.0

Last pushed

Feb 02, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/UKPLab/PeerQA"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.