CSR improves LLM calibration by combining binary correctness rewards with a semantic calibration reward that promotes agreement on correct rollouts and discourages spurious consistency on incorrect ones, outperforming verbalized confidence baselines on ECE and AUROC across in- and out-of-domain QA任务
Title resolution pending
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
-
Calibrating LLMs with Semantic-level Reward
CSR improves LLM calibration by combining binary correctness rewards with a semantic calibration reward that promotes agreement on correct rollouts and discourages spurious consistency on incorrect ones, outperforming verbalized confidence baselines on ECE and AUROC across in- and out-of-domain QA任务