GUIDE: Generative Utility Inference and Decision Engine

2026-09-10

AI Summary

为解决AI对齐中用户偏好测量难题，GUIDE通过结合贝叶斯自适应采样和符号表示学习的方法，在对话中高效推断用户偏好。

Abstract

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 extensible type system of transforms on a parameterized preference state. GUIDE produces domain-specific preference representations through an initialization process using symbolic rule-based learning to capture world knowledge and set priors over preference dimensions grounded in data about decision alternatives. The architecture provides observability and steerability to facilitate deployment and analyze elicitation processes. In silico experiments on investment portfolio optimization demonstrate that GUIDE improves cold-start and minimizes recommendation regret consistently within early elicitation interactions across user personas compared to prior work, LLM-only baselines, and ablated GUIDE versions.

Problem

• human preferences
• AI alignment
• multidimensional preferences
• domain knowledge

Innovation

• Bayesian adaptive sampling
• symbolic representation learning
• extensible type system
• preference state
• rule-based learning