HowieHwong/TrustLLM

[ICML 2024] TrustLLM: Trustworthiness in Large Language Models

52
/ 100
Established

Provides comprehensive evaluation across six trustworthiness dimensions (truthfulness, safety, fairness, robustness, privacy, machine ethics) via a Python toolkit with modular task pipelines and support for 16+ mainstream LLMs through native APIs and external inference providers (Replicate, DeepInfra, Azure OpenAI). The benchmark aggregates 30+ datasets covering these dimensions, enabling researchers to systematically assess model trustworthiness using standardized metrics and an open leaderboard.

619 stars and 62 monthly downloads. No commits in the last 6 months. Available on PyPI.

Stale 6m
Maintenance 2 / 25
Adoption 14 / 25
Maturity 18 / 25
Community 18 / 25

How are scores calculated?

Stars

619

Forks

66

Language

Python

License

MIT

Last pushed

Jun 24, 2025

Monthly downloads

62

Commits (30d)

0

Dependencies

20

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/HowieHwong/TrustLLM"

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