GitHub - Emmanuel-Rono/LLM-Regression-evaluation: An agentic framework for semantic regression testing of large language models, designed to detect behavioral drift across model versions using tolerance-based oracles instead of brittle string assertions.

Branches Tags

Name		Name	Last commit message	Last commit date
Latest commit History 4 Commits
.idea		.idea
agents		agents
config		config
evaluations		evaluations
llm		llm
tests		tests
.gitignore		.gitignore
main.py		main.py
requirements.txt		requirements.txt

About

An agentic framework for semantic regression testing of large language models, designed to detect behavioral drift across model versions using tolerance-based oracles instead of brittle string assertions.