TRI·TFM v3.0 Framework
ストックにはログインが必要です
Deterministic, LLM-as-a-Judge evaluation framework.
Artificial Intelligence
GitHub
An open-source, mathematically proven evaluation pipeline for LLMs and RAG systems. We eliminate metric hallucination by locking T=0.0 and applying a dynamic weight matrix (Bal = 0.75F - 0.25B) to score Facts, Bias, and Narrative deterministically.
投票数: 0