Review
Aug 2026
Claim-Level Confidence Calibration for Reliable Decision Making with Large Language Models
Claim-level decomposition combined with post-hoc calibration reduces expected calibration error on factual questions while exposing failure modes on adversarial false-premise questions where decision-makers most need reliable uncertainty estimates.
Toghrul Abbasli, Kentaroh Toyoda, Yuan Wang et al.
· 0 citations