A self-critique and refinement framework with word-level feedback cuts unfaithfulness rates in LLM explanations by about 19 points on average, but gains may partly reflect the word-presence evaluation metric.
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
-
Self-Critique and Refinement for Faithful Natural Language Explanations
A self-critique and refinement framework with word-level feedback cuts unfaithfulness rates in LLM explanations by about 19 points on average, but gains may partly reflect the word-presence evaluation metric.