Few-Shot Recalibration of Language Models

arXiv:2403.18286v1 Announce Type: cross
Abstract: Recent work has uncovered promising ways to extract well-calibrated confidence estimates from language models (LMs), where the model's confidence score reflects how likely it is to be correct. However, while LMs may appear well-calibrated over broad distributions, this often hides significant miscalibration within narrower slices (e.g., systemic over-confidence in math can balance out systemic under-confidence in history, yielding perfect calibration in aggregate). To attain well-calibrated confidence estimates for any slice of a distribution, we propose …

abstract arxiv confidence cs.ai cs.cl cs.lg extract few-shot however language language models lms math type work