The proposed Faithful-Refiner, combining syntactic parsing, quantifier and consistency checks, logical-relation guidance, and detailed proof feedback, raises explanation refinement rates on three NLI benchmarks by large margins over the prior Explanation-Refiner baseline.
Title resolution pending
1 Pith paper cite this work, alongside 17 external citations. Polarity classification is still indexing.
1
Pith paper citing it
17
external citations · OpenAlex
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Faithful and Robust LLM-Driven Theorem Proving for NLI Explanations
The proposed Faithful-Refiner, combining syntactic parsing, quantifier and consistency checks, logical-relation guidance, and detailed proof feedback, raises explanation refinement rates on three NLI benchmarks by large margins over the prior Explanation-Refiner baseline.