2 papers
cs.CY2025
Reinforcement Learning from Human Feedback: Whose Culture, Whose Values, Whose Perspectives?
Kristian González Barman, Simon Lohse, Henk de Regt
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…
physics.data-an2025
Large Physics Models: Towards a collaborative approach with Large Language Models and Foundation Models
Kristian G. Barman, Sascha Caron, Emily Sullivan +19
This paper explores ideas and provides a potential roadmap for the development and evaluation of physics-specific large-scale AI models, which we call Large Physics Models (LPMs).…