一作NeurIPS 2026Poster
How do Small Transformer Models Learn Hard Math Tasks?
Eshika Saxena · Kristin E. Lauter
首次获取该候选人的完整档案及 StartLux 评估共 20 积分；每位用户单独解锁，之后查看免费。主动刷新 20 积分。
实时查找电子邮箱，费用不超过20积分；未找到邮箱不扣费。
Eshika Saxena · Kristin E. Lauter
Bhaktipriya Radharapu · Eshika Saxena · Kenneth Li · Chenxi Whitehouse · Adina Williams · Nicola Cancedda
As LLM-based judges become integral to industry applications, obtaining well-calibrated uncertainty estimates efficiently has become critical for production deployment. However, existing techniques, such as verbalized confidence and multi-generation methods, are often either poorly calibrated or...