Related papers: GUIDE: Generative Utility Inference and Decision Engine

GUIDE: Generative Utility Inference and Decision Engine

URL: http://arxiv.org/abs/2609.12137v1
Date: Thu, 10 Sep 2026 19:12:09 GMT
Title: GUIDE: Generative Utility Inference and Decision Engine
Abstract summary: We introduce GUIDE, an LLM-driven elicitation architecture that infers user preferences through conversations.<n> GUIDE generalizes adaptive sampling to diverse elicitation questions.<n>It produces domain-specific preference representations through a symbolic rule-based learning process.
Score: 47.51965836398949
License: http://creativecommons.org/licenses/by/4.0/
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 papers

Think2Go: Generative Next POI Recommendation with LLM Reasoning [57.37706163990998]
Next Point-of-Interest (POI) recommendation task focuses on mining user behavioral preference patterns from historical check-ins to provide personalized suggestions for the next destination.<n>Existing methods rely on shallow contextual information and handcrafted feature interactions to predict the next POI.<n>We propose Think2Go, a novel generative next POI recommendation framework, which enhances the model's comprehension of SID representations and explores diverse spatial-temporal patterns via test-time computational scaling.
arXiv Detail & Related papers (2026-07-31T03:52:20Z)
RecNet: Self-Evolving Preference Propagation for Agentic Recommender Systems [109.9061591263748]
RecNet is a self-evolving preference propagation framework for recommender systems.<n>It proactively propagates real-time preference updates across related users and items.<n>In the backward phase, the feedback-driven propagation optimization mechanism simulates a multi-agent reinforcement learning framework.
arXiv Detail & Related papers (2026-01-29T12:14:31Z)
GEM: Generative Entropy-Guided Preference Modeling for Few-shot Alignment of LLMs [5.1816417820270075]
In this paper, we propose a generative entropy-guided preference modeling approach named GEM for large language models (LLMs)<n>Instead of training a discriminative reward model on preference data, we directly train the LLM to internalize a closed-loop optimization architecture.<n> Experiments on general benchmarks and domain-specific tasks demonstrate that our GEM achieves significant improvements with few-shot preference data.
arXiv Detail & Related papers (2025-11-17T06:04:47Z)
A Novel Self-Evolution Framework for Large Language Models [18.62332474172811]
We propose a novel Dual-Phase Self-Evolution framework to jointly optimize user preference adaptation and domain-specific competence.<n>Experiments across general NLP benchmarks and long-term dialogue tasks demonstrate that DPSE consistently outperforms Supervised Fine-Tuning, Preference Optimization, and Memory-Augmented baselines.
arXiv Detail & Related papers (2025-07-21T06:30:39Z)
Churn-Aware Recommendation Planning under Aggregated Preference Feedback [6.261444979025644]
We study a sequential decision-making problem motivated by recent regulatory and technological shifts.<n>We introduce the Rec-APC model, in which an anonymous user is drawn from a known prior over latent user types.<n>We prove that optimal policies converge to pure exploitation in finite time and propose a branch-and-bound algorithm to efficiently compute them.
arXiv Detail & Related papers (2025-07-06T19:22:47Z)
What Makes LLMs Effective Sequential Recommenders? A Study on Preference Intensity and Temporal Context [56.590259941275434]
RecPO is a preference optimization framework for sequential recommendation.<n>It exploits adaptive reward margins based on inferred preference hierarchies and temporal signals.<n>It mirrors key characteristics of human decision-making: favoring timely satisfaction, maintaining coherent preferences, and exercising discernment under shifting contexts.
arXiv Detail & Related papers (2025-06-02T21:09:29Z)
Large Language Model Empowered Recommendation Meets All-domain Continual Pre-Training [60.38082979765664]
CPRec is an All-domain Continual Pre-Training framework for Recommendation.<n>It holistically align LLMs with universal user behaviors through the continual pre-training paradigm.<n>We conduct experiments on five real-world datasets from two distinct platforms.
arXiv Detail & Related papers (2025-04-11T20:01:25Z)
Few-shot Steerable Alignment: Adapting Rewards and LLM Policies with Neural Processes [50.544186914115045]
Large language models (LLMs) are increasingly embedded in everyday applications.<n> Ensuring their alignment with the diverse preferences of individual users has become a critical challenge.<n>We present a novel framework for few-shot steerable alignment.
arXiv Detail & Related papers (2024-12-18T16:14:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.