DecMetrics scores claim decompositions for completeness, correctness, and semantic entropy, and uses them as rewards to train a small T5 model, but the evaluation is circular and it does not lift downstream fact-checking accuracy.
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
REJECT 1representative citing papers
citing papers explorer
-
DecMetrics: Structured Claim Decomposition Scoring for Factually Consistent LLM Outputs
DecMetrics scores claim decompositions for completeness, correctness, and semantic entropy, and uses them as rewards to train a small T5 model, but the evaluation is circular and it does not lift downstream fact-checking accuracy.