Reinforcement Learning from Human Feedback: Whose Culture, Whose Values, Whose Perspectives?
This addresses ethical and inclusivity issues in AI development for diverse global users, but it is incremental as it builds on existing RLHF frameworks.
The paper tackles the problem of cultural and value biases in Reinforcement Learning from Human Feedback (RLHF) for Large Language Models (LLMs), proposing pluralistic approaches to make RLHF more responsive to human needs and outlining actionable steps for improvement.
We argue for the epistemic and ethical advantages of pluralism in Reinforcement Learning from Human Feedback (RLHF) in the context of Large Language Models (LLM). Drawing on social epistemology and pluralist philosophy of science, we suggest ways in which RHLF can be made more responsive to human needs and how we can address challenges along the way. The paper concludes with an agenda for change, i.e. concrete, actionable steps to improve LLM development.