R_REDDYX.XYZ
AIPython★ 636⑂ 69 forksMIT

HowieHwong/TrustLLM

TRUSTLLM: EVALUATION OF LLM TRUSTWORTHINESS

TrustLLM — a toolkit for assessing LLM trustworthiness, presented at ICML 2024. It includes benchmark suites, metrics, and datasets for measuring hallucinations, bias, and answer reliability.

// KEY FEATURES

  • Provides benchmark suites for measuring hallucinations and factuality of LLMs.
  • Includes metrics for assessing bias, toxicity, and fairness of model outputs.
  • Enables automated evaluation via CLI and API, producing detailed JSON reports.
  • Integrates with HuggingFace, LangChain, and other frameworks for quick plug‑and‑play.
#ai#benchmark#dataset#evaluation#large-language-models#llm#natural-language-processing#nlp#pypi-package#toolkit#trustworthy-ai#trustworthy-machine-learning
Open on GitHub →

New repositories every 30 minutes

REDDYX AI scans GitHub 24/7 and ships the best AI/ML/Web3 projects to Telegram.

Join on Telegram
← Full catalog·Full index

// SIMILAR REPOSITORIES

AI firewall for MCP★ 636BEST LIST OF AGENT SERVICES★ 6363D ENGINE DRIVEN BY AI AGENTS★ 636Pets for AI Agents★ 635NODETOOL: YOUR AI WORKSPACE★ 637nWave: AI Agents for Coding★ 635

← FULL CATALOG

HowieHwong/TrustLLM — Trustllm: Evaluation OF LLM…