Social Choice for AI Alignment: Dealing with Diverse Human Feedback
arxiv(2024)
摘要
Foundation models such as GPT-4 are fine-tuned to avoid unsafe or otherwise
problematic behavior, so that, for example, they refuse to comply with requests
for help with committing crimes or with producing racist text. One approach to
fine-tuning, called reinforcement learning from human feedback, learns from
humans' expressed preferences over multiple outputs. Another approach is
constitutional AI, in which the input from humans is a list of high-level
principles. But how do we deal with potentially diverging input from humans?
How can we aggregate the input into consistent data about ”collective”
preferences or otherwise use it to make collective choices about model
behavior? In this paper, we argue that the field of social choice is well
positioned to address these questions, and we discuss ways forward for this
agenda, drawing on discussions in a recent workshop on Social Choice for AI
Ethics and Safety held in Berkeley, CA, USA in December 2023.
更多查看译文
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