Beyond Expectations: Quantile-Guided Alignment for Risk-Calibrated Language Models

NeurIPSSpotlight2025

Authors: Xinran Wang, Jin Du, Azal Ahmad Khan, Qi Le, Enmao Diao, Jiawei Zhou, Jie Ding, Ali Anwar
Venue: NeurIPS 2025
Track: Spotlight

TL;DR

Large language models can generate rare but catastrophic outputs, such as harmful conversations or insecure code…

Opening excerpt from the authors’ abstract. source

Read the paper

OpenReview

Topics

large language model language model alignment

← All NeurIPS 2025 Spotlight papers · Browse the whole archive