Show HN: I built a small audit layer for LLM-as-judge decisions(github.com)

2 pointsby ML0037il y a 16 jours0 comments

Show HN: I built a small audit layer for LLM-as-judge decisions

https://github.com/MatteoLeonesi/claim-memory-graph-sdk

I made this while checking model graded answer and helped me to check the odd cases by hand. Not sure if it’s useful to anyone else.

TL;DR: it breaks an LLM judge run into claims->evidence->verdicts and flags when a verdict is not supported by the evidence, so i can check it manually.

0 comments

—