@inproceedings{luo-etal-2025-large,
title = "How Do Large Language Models Perform in Dynamical System Modeling",
author = "Luo, Xiao and
Chen, Binqi and
Wang, Haixin and
Xiao, Zhiping and
Zhang, Ming and
Sun, Yizhou",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2025",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-naacl.50/",
doi = "10.18653/v1/2025.findings-naacl.50",
pages = "866--880",
ISBN = "979-8-89176-195-7",
abstract = "This paper studies the problem of dynamical system modeling, which involves the evolution of multiple interacting objects. Recent data-driven methods often utilize graph neural networks (GNNs) to learn these interactions by optimizing the neural network in an end-to-end fashion. While large language models (LLMs) have shown exceptional zero-shot performance across various applications, their potential for modeling dynamical systems has not been extensively explored. In this work, we design prompting techniques for dynamical system modeling and systematically evaluate the capabilities of LLMs on two tasks, including dynamic forecasting and relational reasoning. An extensive benchmark LLM4DS across nine datasets is built for performance comparison. Our extensive experiments yield several key findings: (1) LLMs demonstrate competitive performance without training compared to state-of-the-art methods in dynamical system modeling. (2) LLMs effectively infer complex interactions among objects to capture system evolution. (3) Prompt engineering plays a crucial role in enabling LLMs to accurately understand and predict the evolution of systems."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="luo-etal-2025-large">
<titleInfo>
<title>How Do Large Language Models Perform in Dynamical System Modeling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiao</namePart>
<namePart type="family">Luo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Binqi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haixin</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiping</namePart>
<namePart type="family">Xiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ming</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yizhou</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: NAACL 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-195-7</identifier>
</relatedItem>
<abstract>This paper studies the problem of dynamical system modeling, which involves the evolution of multiple interacting objects. Recent data-driven methods often utilize graph neural networks (GNNs) to learn these interactions by optimizing the neural network in an end-to-end fashion. While large language models (LLMs) have shown exceptional zero-shot performance across various applications, their potential for modeling dynamical systems has not been extensively explored. In this work, we design prompting techniques for dynamical system modeling and systematically evaluate the capabilities of LLMs on two tasks, including dynamic forecasting and relational reasoning. An extensive benchmark LLM4DS across nine datasets is built for performance comparison. Our extensive experiments yield several key findings: (1) LLMs demonstrate competitive performance without training compared to state-of-the-art methods in dynamical system modeling. (2) LLMs effectively infer complex interactions among objects to capture system evolution. (3) Prompt engineering plays a crucial role in enabling LLMs to accurately understand and predict the evolution of systems.</abstract>
<identifier type="citekey">luo-etal-2025-large</identifier>
<identifier type="doi">10.18653/v1/2025.findings-naacl.50</identifier>
<location>
<url>https://aclanthology.org/2025.findings-naacl.50/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>866</start>
<end>880</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T How Do Large Language Models Perform in Dynamical System Modeling
%A Luo, Xiao
%A Chen, Binqi
%A Wang, Haixin
%A Xiao, Zhiping
%A Zhang, Ming
%A Sun, Yizhou
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Findings of the Association for Computational Linguistics: NAACL 2025
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-195-7
%F luo-etal-2025-large
%X This paper studies the problem of dynamical system modeling, which involves the evolution of multiple interacting objects. Recent data-driven methods often utilize graph neural networks (GNNs) to learn these interactions by optimizing the neural network in an end-to-end fashion. While large language models (LLMs) have shown exceptional zero-shot performance across various applications, their potential for modeling dynamical systems has not been extensively explored. In this work, we design prompting techniques for dynamical system modeling and systematically evaluate the capabilities of LLMs on two tasks, including dynamic forecasting and relational reasoning. An extensive benchmark LLM4DS across nine datasets is built for performance comparison. Our extensive experiments yield several key findings: (1) LLMs demonstrate competitive performance without training compared to state-of-the-art methods in dynamical system modeling. (2) LLMs effectively infer complex interactions among objects to capture system evolution. (3) Prompt engineering plays a crucial role in enabling LLMs to accurately understand and predict the evolution of systems.
%R 10.18653/v1/2025.findings-naacl.50
%U https://aclanthology.org/2025.findings-naacl.50/
%U https://doi.org/10.18653/v1/2025.findings-naacl.50
%P 866-880
Markdown (Informal)
[How Do Large Language Models Perform in Dynamical System Modeling](https://aclanthology.org/2025.findings-naacl.50/) (Luo et al., Findings 2025)
ACL