RALC is a retrieval-augmented rewriting pipeline that improves linguistic faithfulness and calibration of LLM outputs by up to 66% and 58% on QA benchmarks.
Extending confidence calibration to generalised measures of variation.arXiv preprint arXiv:2602.12975, 2026
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Retrieval-Augmented Linguistic Calibration
RALC is a retrieval-augmented rewriting pipeline that improves linguistic faithfulness and calibration of LLM outputs by up to 66% and 58% on QA benchmarks.