Provable Limits and Certified Deferral for Verbalized Uncertainty in Small Language Models
Small open-weight language models increasingly run in private, offline, and cost-sensitive settings, where the key deployment question is not only what a model answers but when it should defer to a human. We study whether verbalized confidence can support risk-controlled deferral, evaluating eleven instruction-tuned models from three families, 0.5B to 14B parameters, on ARC-Challenge and…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
