A Guide to Large Language Models in Modeling and Simulation: From Core Techniques to Critical Challenges

TL;DR

This paper provides practical guidance on effectively integrating large language models into modeling and simulation workflows, addressing common pitfalls, hyper-parameter tuning, and evaluation strategies to improve outcomes.

Contribution

It offers a comprehensive, pragmatic framework for using LLMs in M&S, highlighting best practices, diagnostic methods, and addressing misconceptions and challenges.

Findings

Naive data addition can harm LLM performance

Temperature 0 does not guarantee determinism

Proper evaluation is crucial for effective LLM use in M&S

Abstract

Large language models (LLMs) have rapidly become familiar tools to researchers and practitioners. Concepts such as prompting, temperature, or few-shot examples are now widely recognized, and LLMs are increasingly used in Modeling & Simulation (M&S) workflows. However, practices that appear straightforward may introduce subtle issues, unnecessary complexity, or may even lead to inferior results. Adding more data can backfire (e.g., deteriorating performance through model collapse or inadvertently wiping out existing guardrails), spending time on fine-tuning a model can be unnecessary without a prior assessment of what it already knows, setting the temperature to 0 is not sufficient to make LLMs deterministic, providing a large volume of M&S data as input can be excessive (LLMs cannot attend to everything) but naive simplifications can lose information. We aim to provide comprehensive and practical guidance on how to use LLMs, with an emphasis on M&S applications. We discuss common sources of confusion, including non-determinism, knowledge augmentation (including RAG and LoRA), decomposition of M&S data, and hyper-parameter settings. We emphasize principled design choices, diagnostic strategies, and empirical evaluation, with the goal of helping modelers make informed decisions about when, how, and whether to rely on LLMs.