The paper proposes HCAT, a human-calibrated evaluation framework for RAG models, combining automated tests, embedding metrics, and conformal prediction.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Human-Calibrated Automated Testing and Validation of Generative Language Models
The paper proposes HCAT, a human-calibrated evaluation framework for RAG models, combining automated tests, embedding metrics, and conformal prediction.