conftrace_

ai alignment

34 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (12) value alignment (6) ai safety (6) reinforcement learning from human feedback (5) scalable oversight (4) human feedback (4) reward function (4) model alignment (4) weak-to-strong generalization (3) preference learning (3)

Papers

Improving Alignment and Robustness with Circuit Breakers NeurIPS 2024 On the Essence and Prospect: An Investigation of Alignment Approaches for Big Models IJCAI 2024 Pedagogical Alignment of Large Language Models EMNLP 2024 Position: Social Choice Should Guide AI Alignment in Dealing with Diverse Human Feedback ICML 2024 ProgressGym: Alignment with a Millennium of Moral Progress NeurIPS 2024 SoFA: Shielded On-the-fly Alignment via Priority Rule Following ACL 2024 RealBehavior: A Framework for Faithfully Characterizing Foundation Models’ Human-like Behavior Mechanisms EMNLP 2023 Consequences of Misaligned AI NeurIPS 2020 AGI Safety Literature Review IJCAI 2018