Learning Transferable Latent User Preferences for Human-Aligned Decision Making

ArXi:2605.12682v1 Announce Type: new Large language models (LLMs) are increasingly used as reasoning modules in many applications. While they are efficient in certain tasks, LLMs often struggle to produce human-aligned solutions. Human-aligned decision making requires accounting for both explicitly stated goals and latent user preferences that shape how ambiguous situations should be resolved.