Show HN: I built a small audit layer for LLM-as-judge decisions(github.com)
github.com
Show HN: I built a small audit layer for LLM-as-judge decisions
https://github.com/MatteoLeonesi/claim-memory-graph-sdk
0 コメント
—
https://github.com/MatteoLeonesi/claim-memory-graph-sdk
—
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.