Semantic Self-Distillation for Language Model Uncertainty

ArXi:2602.04577v2 Announce Type: replace Large language models present challenges for principled uncertainty quantification, in part due to their complexity and the diversity of their outputs. Semantic dispersion, or the variance in the meaning of sampled answers, has been proposed as a useful proxy for model uncertainty, but the associated computational cost prohibits its use in latency-critical applications.