Leveraging Large Language Models for Preference-Based Sequence Prediction

Michaela Tecson, Daphne Chen, Michelle Zhao, Zackory Erickson, Reid Simmons

2025

Abstract

We present a novel approach to leveraging Large Language Models (LLMs) for action prediction in meal preparation sequences, with a focus on tailoring predictions based on user preferences. We introduce methods using OpenAI’s GPT-4o model to predict subsequent actions in a sequence by providing different forms of context such as sequences from other participants or prior sequences of the test participant. Our approach outperforms baseline methods, including Aggregate Long Short-Term Memory (LSTM) and mixture-of-experts (MoE) models, by up to 33.8% by leveraging the LLM’s ability to adapt predictions based on minimal prior context. We highlight the generalizability of the method across different cooking domains by analyzing the results on two different cooking datasets. This adaptability will be useful for assistive systems aiming to support older adults, especially those with Mild Cognitive Impairments (MCI), in completing complex, sequential tasks in ways that align with the user’s preferences. The full prompts used in this work can be found at the project webpage: sites.google.com/view/preference-based-prediction.

Paper Citation

in Harvard Style

Tecson M., Chen D., Zhao M., Erickson Z. and Simmons R. (2025). Leveraging Large Language Models for Preference-Based Sequence Prediction. In Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART; ISBN 978-989-758-737-5, SciTePress, pages 519-532. DOI: 10.5220/0013190200003890

in Bibtex Style

@conference{icaart25,
author={Michaela Tecson and Daphne Chen and Michelle Zhao and Zackory Erickson and Reid Simmons},
title={Leveraging Large Language Models for Preference-Based Sequence Prediction},
booktitle={Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART},
year={2025},
pages={519-532},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013190200003890},
isbn={978-989-758-737-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART
TI - Leveraging Large Language Models for Preference-Based Sequence Prediction
SN - 978-989-758-737-5
AU - Tecson M.
AU - Chen D.
AU - Zhao M.
AU - Erickson Z.
AU - Simmons R.
PY - 2025
SP - 519
EP - 532
DO - 10.5220/0013190200003890
PB - SciTePress