作者位次 #3/4ICLR 2026Poster· General Machine Learning / Probabilistic Methods
Don’t Pass@k: A Bayesian Framework for Large Language Model Evaluation
Mohsen Hariri · Amirhossein Samandar · Michael Hinczewski · Vipin Chaudhary
评测与基准OpenReview
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。
Mohsen Hariri · Amirhossein Samandar · Michael Hinczewski · Vipin Chaudhary
Mohsen Hariri · Michael Hinczewski · Jing Ma · Vipin Chaudhary
Test-time scaling evaluates reasoning LLMs by sampling multiple outputs per prompt, but ranking models in this regime remains underexplored. We formalize dense benchmark ranking under test-time scaling and introduce Scorio, a library that implements statistical ranking methods such as paired-comp...