SOURCE-LINKED INTELLIGENCE

GUIDE: Generative Utility Inference and Decision Engine

arXiv · AI, language, vision and robotics · article · Sep 10, 2026 · UTC

Measuring the preferences of human users remains a fundamental challenge of AI alignment. Existing elicitation approaches struggle to efficiently discover multidimensional preferences or accurately ground these inferences in domain knowledge. To address this, we introduce GUIDE, an LLM-driven elicitation architecture that infers user preferences through conversations by combining Bayesian adaptive sampling for question selection and symbolic representation learning to initialize domain-specific preference models. GUIDE generalizes adaptive sampling to diverse elicitation questions through an e

Read original source ↗ Open in workspace

recordType

paper

region

Global