Cultural Alignment in Large Language Models Using Soft Prompt Tuning
This work proposes a deployment-friendly approach that encodes cultural behavior in short, tunable soft prompts optimized with Differential Evolution (DE), while keeping model weights frozen and requiring no preference data.
Reem I. Masoud, Martin Ferianc, Philip C. Treleaven et al.
· arXiv.org · 4 citations
· ⚡1