Collective Constitutional AI: Aligning a Language Model with Public Input

Saffron Huang,Divya Siddarth,Liane Lovitt,Thomas I. Liao,Esin Durmus,Alex Tamkin,Deep Ganguli

PROCEEDINGS OF THE 2024 ACM CONFERENCE ON FAIRNESS, ACCOUNTABILITY, AND TRANSPARENCY, ACM FACCT 2024（2024）

引用 2|浏览4

关键词

human-centered AI,participatory AI,reinforcement learning from human feedback,AI ethics,value alignment,collective alignment,AI alignment,generative AI,AI bias

AI 理解论文

溯源树

样例

生成溯源树，研究论文发展脉络

Chat Paper

正在生成论文摘要