Knowledge Tree
Relations (1)
related 1.00 — strongly supporting 1 fact
The concepts are related because the BAFH framework evaluates the LLaMA model's performance in classifying hallucination types against the MIND baseline, as described in [1].
Facts (1)
Sources
EdinburghNLP/awesome-hallucination-detection - GitHub github.com 1 fact
procedureThe BAFH framework is a lightweight method that trains a feedforward classifier on hidden states of Large Language Models to determine belief states and classify hallucination types, as evaluated against MIND and SAR baselines using Gemma-2, Llama-3.1, and Mistral models.