GitHub - souvikghosh/llm-eval: LLM evaluation & red-teaming toolkit — faithfulness scoring, hallucination detection, adversarial probing, and LLM-as-judge. Built by a QA engineer for AI systems.

Branches Tags

Name		Name	Last commit message	Last commit date
Latest commit History 6 Commits
examples		examples
llm_eval		llm_eval
tests		tests
.env.example		.env.example
.gitignore		.gitignore
Dockerfile		Dockerfile
pyproject.toml		pyproject.toml

About

LLM evaluation & red-teaming toolkit — faithfulness scoring, hallucination detection, adversarial probing, and LLM-as-judge. Built by a QA engineer for AI systems.