conftrace_

ai alignment

28 papers

Explore in graph

Co-occurring keywords

large language model (13587) value alignment (91) ai safety (235) scalable oversight (9) human feedback (161) reward function (291) model alignment (226) reinforcement learning from human feedback (278) preference learning (418) social choice theory (28)

Papers

RealBehavior: A Framework for Faithfully Characterizing Foundation Models’ Human-like Behavior Mechanisms EMNLP 2023
Consequences of Misaligned AI NIPS 2020
AGI Safety Literature Review IJCAI 2018