A large-scale comparison of six hallucination detection metric families across 37 models and five decoding methods finds most metrics align poorly with human judgments, with GPT-4-based evaluation performing best.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Evaluating Evaluation Metrics -- The Mirage of Hallucination Detection
A large-scale comparison of six hallucination detection metric families across 37 models and five decoding methods finds most metrics align poorly with human judgments, with GPT-4-based evaluation performing best.