cvs-health/langfair

LangFair is a Python library for conducting use-case level LLM bias and fairness assessments

70
/ 100
Verified

Implements a "Bring Your Own Prompts" (BYOP) approach enabling use-case-specific fairness evaluations with output-based metrics across toxicity, stereotype association, and counterfactual parity—without requiring model internals access. Integrates with any LangChain LLM provider and offers both granular metric classes (ToxicityMetrics, StereotypeMetrics, CounterfactualMetrics) and an AutoEval convenience wrapper for streamlined text generation and summarization assessments.

255 stars and 661 monthly downloads. Available on PyPI.

Maintenance 10 / 25
Adoption 16 / 25
Maturity 25 / 25
Community 19 / 25

How are scores calculated?

Stars

255

Forks

41

Language

Python

License

Last pushed

Jan 09, 2026

Monthly downloads

661

Commits (30d)

0

Dependencies

17

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/cvs-health/langfair"

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