# Decisive: Guiding User Decisions with Optimal Preference Elicitation from Unstructured Documents

arXiv: https://arxiv.org/abs/2604.18122 · HTML: https://mlsanity.com/paper/2604.18122/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 34 references that are in the map.
- First posted on arXiv 20 Apr 2026.

## Builds on (most cited first, 19 of 19)

- [Large language models in healthcare and medical domain: A review](https://mlsanity.com/paper/2401.06775/) (2023)
- [STaR-GATE: Teaching Language Models to Ask Clarifying Questions](https://mlsanity.com/paper/2403.19154/) (2024)
- [Clarify When Necessary: Resolving Ambiguity Through Interaction with LMs](https://mlsanity.com/paper/2311.09469/) (2023)
- [Determinants of LLM-assisted Decision-Making](https://mlsanity.com/paper/2402.17385/) (2024)
- [UMBRELA: UMbrela is the (Open-Source Reproduction of the) Bing RELevance Assessor](https://mlsanity.com/paper/2406.06519/) (2024)
- [Decision-Making Behavior Evaluation Framework for LLMs under Uncertain Context](https://mlsanity.com/paper/2406.05972/) (2024)
- [Towards Human-AI Deliberation: Design and Evaluation of LLM-Empowered Deliberative AI for AI-Assisted Decision-Making](https://mlsanity.com/paper/2403.16812/) (2024)
- [Bayesian Preference Elicitation with Language Models](https://mlsanity.com/paper/2403.05534/) (2024)
- [Active Preference Inference using Language Models and Probabilistic Reasoning](https://mlsanity.com/paper/2312.12009/) (2023)
- [Are Emily and Greg Still More Employable than Lakisha and Jamal? Investigating Algorithmic Hiring Bias in the Era of ChatGPT](https://mlsanity.com/paper/2310.05135/) (2023)
- [ChoiceMates: Supporting Unfamiliar Online Decision-Making with Multi-Agent Conversational Interactions](https://mlsanity.com/paper/2310.01331/) (2023)
- [JobFair: A Framework for Benchmarking Gender Hiring Bias in Large Language Models](https://mlsanity.com/paper/2406.15484/) (2024)
- [Bayesian Optimization with LLM-Based Acquisition Functions for Natural Language Preference Elicitation](https://mlsanity.com/paper/2405.00981/) (2024)
- [Language Models are Alignable Decision-Makers: Dataset and Application to the Medical Triage Domain](https://mlsanity.com/paper/2406.06435/) (2024)
- [Large Language Models for Supply Chain Decisions](https://mlsanity.com/paper/2507.21502/) (2025)
- [DecisionFlow: Advancing Large Language Model as Principled Decision Maker](https://mlsanity.com/paper/2505.21397/) (2025)
- [InfoQuest: Evaluating Multi-Turn Dialogue Agents for Open-Ended Conversations with Hidden Context](https://mlsanity.com/paper/2502.12257/) (2025)
- [TO-GATE: Clarifying Questions and Summarizing Responses with Trajectory Optimization for Eliciting Human Preference](https://mlsanity.com/paper/2506.02827/) (2025)
- [Do LLMs Recognize Your Latent Preferences? A Benchmark for Latent Information Discovery in Personalized Interaction](https://mlsanity.com/paper/2510.17132/) (2025)

## Abstract (arXiv)

Decision-making is a cognitively intensive task that requires synthesizing relevant information from multiple unstructured sources, weighing competing factors, and incorporating subjective user preferences. Existing methods, including large language models and traditional decision-support systems, fall short: they often overwhelm users with information or fail to capture nuanced preferences accurately. We present Decisive, an interactive decision-making framework that combines document-grounded reasoning with Bayesian preference inference. Our approach grounds decisions in an objective option-scoring matrix extracted from source documents, while actively learning a user's latent preference vector through targeted elicitation. Users answer pairwise tradeoff questions adaptively selected to maximize information gain over the final decision. This process converges efficiently, minimizing user effort while ensuring recommendations remain transparent and personalized. Through extensive experiments, we demonstrate that our approach significantly outperforms both general-purpose LLMs and existing decision-making frameworks achieving up to 20% improvement in decision accuracy over strong baselines across domains.