Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Jovine, Adam S., Ye, Tinghan, Bahk, Francis, Wang, Jingjing, Ford, Matthew, Shmoys, David B., Frazier, Peter I.
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2510.25799
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913175308337152
author Jovine, Adam S.
Ye, Tinghan
Bahk, Francis
Wang, Jingjing
Ford, Matthew
Shmoys, David B.
Frazier, Peter I.
author_facet Jovine, Adam S.
Ye, Tinghan
Bahk, Francis
Wang, Jingjing
Ford, Matthew
Shmoys, David B.
Frazier, Peter I.
contents Human experts often struggle to select the best option from a large set of items with multiple competing objectives, a process bottlenecked by the difficulty of formalizing complex, implicit preferences. To address this, we introduce LISTEN (LLM-based Iterative Selection with Trade-off Evaluation from Natural-language), an agentic LLM-based framework that treats the LLM as a decision-making agent capable of iteratively refining its internal preference model and taking actions (e.g., proposing utilities or selecting candidates) to maximize alignment with a user's implicit goals. To operate within LLM constraints like context windows and inference costs, we propose two iterative algorithms: LISTEN-U, which uses the LLM to refine a parametric utility function, and LISTEN-T, a non-parametric method that performs tournament-style selections over small batches of solutions. Evaluated on diverse tasks including flight booking, shopping, and exam scheduling, our results show LISTEN-U excels when preferences are parametrically aligned (a property we measure with a novel concordance metric), while LISTEN-T offers more robust performance overall. This work explores a promising direction for steering complex multi-objective decisions directly with natural language, reducing the cognitive burden of traditional preference elicitation. Code is available at https://github.com/AdamJovine/LISTEN; data is available at https://huggingface.co/datasets/AdamJovine/LISTEN-benchmark.
format Preprint
id arxiv_https___arxiv_org_abs_2510_25799
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LISTEN to Your Preferences: An LLM Framework for Multi-Objective Selection
Jovine, Adam S.
Ye, Tinghan
Bahk, Francis
Wang, Jingjing
Ford, Matthew
Shmoys, David B.
Frazier, Peter I.
Computation and Language
Human experts often struggle to select the best option from a large set of items with multiple competing objectives, a process bottlenecked by the difficulty of formalizing complex, implicit preferences. To address this, we introduce LISTEN (LLM-based Iterative Selection with Trade-off Evaluation from Natural-language), an agentic LLM-based framework that treats the LLM as a decision-making agent capable of iteratively refining its internal preference model and taking actions (e.g., proposing utilities or selecting candidates) to maximize alignment with a user's implicit goals. To operate within LLM constraints like context windows and inference costs, we propose two iterative algorithms: LISTEN-U, which uses the LLM to refine a parametric utility function, and LISTEN-T, a non-parametric method that performs tournament-style selections over small batches of solutions. Evaluated on diverse tasks including flight booking, shopping, and exam scheduling, our results show LISTEN-U excels when preferences are parametrically aligned (a property we measure with a novel concordance metric), while LISTEN-T offers more robust performance overall. This work explores a promising direction for steering complex multi-objective decisions directly with natural language, reducing the cognitive burden of traditional preference elicitation. Code is available at https://github.com/AdamJovine/LISTEN; data is available at https://huggingface.co/datasets/AdamJovine/LISTEN-benchmark.
title LISTEN to Your Preferences: An LLM Framework for Multi-Objective Selection
topic Computation and Language
url https://arxiv.org/abs/2510.25799