Broadening Access to Simulations for End-Users via Large Language Models: Challenges and Opportunities

TL;DR

This paper explores how large language models can be used to make simulation tools more accessible to non-expert users by enabling natural language queries and explanations, highlighting opportunities and challenges.

Contribution

It proposes a comprehensive framework for integrating LLMs into simulation access, covering query mapping, reformulation, and result contextualization, and discusses future research directions.

Findings

Identifies key challenges in mapping natural language to simulation models.

Proposes a multi-phase system architecture for end-user simulation access.

Highlights the potential for LLMs to enhance decision-making with simulation results.

Abstract

Large Language Models (LLMs) are becoming ubiquitous to create intelligent virtual assistants that assist users in interacting with a system, as exemplified in marketing. Although LLMs have been discussed in Modeling & Simulation (M&S), the community has focused on generating code or explaining results. We examine the possibility of using LLMs to broaden access to simulations, by enabling non-simulation end-users to ask what-if questions in everyday language. Specifically, we discuss the opportunities and challenges in designing such an end-to-end system, divided into three broad phases. First, assuming the general case in which several simulation models are available, textual queries are mapped to the most relevant model. Second, if a mapping cannot be found, the query can be automatically reformulated and clarifying questions can be generated. Finally, simulation results are produced and contextualized for decision-making. Our vision for such system articulates long-term research opportunities spanning M&S, LLMs, information retrieval, and ethics.