GUIDE: Generative Utility Inference and Decision Engine

arXiv:2609.12137v1 Announce Type: new 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.

Related

• Towards Cognitively-Faithful Decision-Making Models to Improve AI Alignment
• Safety Game: Inference-Time Alignment of Black-Box LLMs via Constrained Optimization
• Large Language Model Few-Shot Prompting with Dilemma Training Outperforms Human Surrogates in Predicting Patient Preferences
• Test-Time Alignment via Hypothesis Reweighting
• A Markov Chain Approach to Preference Alignment

Source: arXiv cs.LG | 2026-09-14