DEV Community

Edwin Lisowski
Edwin Lisowski

Posted on

СontextCheck: LLM & RAG Evaluation Framework

Hi all! We open-sourced a framework for testing LLMs, RAGs, and chatbots. The tool automates query generation, completion requests, regression detection, penetration testing, and hallucination assessment. Designed for developers, researchers, and businesses. And we are looking for contributors! Feel free to try it out for yourself and share your feedback!

Repo on Github

Top comments (1)

Collapse
 
mayank_laddha_21ef3e061ff profile image
Mayank Laddha

Hi, Nice work. I would love to know why most of the frameworks use only "llm as a judge" for hallucination. Why not perplexity and semantic entropy? dev.to/mayank_laddha_21ef3e061ff/d...