Cite
Notes
Only stored in your browser.
Attribution
MoReBench: Evaluating Procedural and Pluralistic Moral Reasoning in Language Models, More than Outcomes
arXiv 2025
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas
from 2 papers
Sydney Levine
Yejin Choi
professor
Bing Liu
Brandon Handoko
Chen Bo Calvin Zhang
Christina Q Knight
Evan Hubinger
Florence Bacus
Harry R. Lloyd
Kyle Fish