Generating Informative Samples for Risk-Averse Fine-Tuning of Downstream Tasks

NeurIPSSpotlight2025

Authors
Heasung Kim, Taekyun Lee, Hyeji Kim, Gustavo De Veciana
Venue
NeurIPS 2025
Track
Spotlight

TL;DR

Risk-averse modeling is critical in safety-sensitive and high-stakes applications…

Opening excerpt from the authors’ abstract. source

Read the paper

Topics

fine-tuning safety

Related NeurIPS papers

← All NeurIPS 2025 Spotlight papers · Browse the whole archive