bryanwilie/pick

PICK: Polished & Informed Candidate Scoring for Knowledge-Grounded Dialogue Systems. This approach reduces hallucination and improves relevance by re-scoring responses, enhancing faithfulness and relevance without extra data or model tuning.

23
/ 100
Experimental

No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 2 / 25
Maturity 9 / 25
Community 12 / 25

How are scores calculated?

Stars

2

Forks

1

Language

Python

License

MIT

Last pushed

Dec 14, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/bryanwilie/pick"

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