arXiv Open Access 2024

Reinforcement Learning from Human Feedback: Whose Culture, Whose Values, Whose Perspectives?

Kristian González Barman Simon Lohse Henk de Regt

Lihat Sumber

Abstrak

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.

Topik & Kata Kunci

cs.CY cs.AI cs.CL cs.HC

Penulis (3)

Kristian González Barman

Simon Lohse

Henk de Regt

Format Sitasi

APA MLA BibTeX

Barman, K.G., Lohse, S., Regt, H.d. (2024). Reinforcement Learning from Human Feedback: Whose Culture, Whose Values, Whose Perspectives?. https://arxiv.org/abs/2407.17482

Akses Cepat

Lihat di Sumber

Informasi Jurnal

Tahun Terbit: 2024
Bahasa: en
Sumber Database: arXiv
Akses: Open Access ✓