A-SHOJAEI/contrastive-qa-verifier-with-adversarial-unanswerable

A dual-encoder system that learns to verify question-answer pair validity through contrastive learning on SQuAD 2.0 and Natural Questions, with adversarial generation of plausible-but-incorrect answers. The model is trained to distinguish between correct answers, near-miss answers (same entity type, wrong entity), and unanswerable questions, enabli

19
/ 100
Experimental
No Package No Dependents
Maintenance 10 / 25
Adoption 0 / 25
Maturity 9 / 25
Community 0 / 25

How are scores calculated?

Stars

Forks

Language

Python

License

MIT

Last pushed

Feb 21, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/A-SHOJAEI/contrastive-qa-verifier-with-adversarial-unanswerable"

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