一作NeurIPS 2026Poster· Social Aspects / Trustworthy Machine Learning
Rank-Constrained Adaptation for Reliable Real-World Performance
Abinitha Gourabathina · Hyewon Jeong · Teya Bergamaschi · Marzyeh Ghassemi · Collin Stultz
社会与人本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。
Abinitha Gourabathina · Hyewon Jeong · Teya Bergamaschi · Marzyeh Ghassemi · Collin Stultz
Abinitha Gourabathina · Inkit Padhi · Manish Nagireddy · Subhajit Chaudhury · Prasanna Sattigeri
For Large Language Models (LLMs) to be reliably deployed, models must effectively know when not to answer: abstain. Reasoning models, in particular, have gained attention for impressive performance on complex tasks. However, reasoning models have been shown to have worse abstention abilities. Tak...