SimLM: Can Language Models Infer Parameters of Physical Systems?

2023/12/21 by Sean Memery, Mirella Lapata, Memery, Sean +3 · 1 citation
Computer Science · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #I.2.7 #I.6 #Natural Language Processing Techniques #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2312.14215

openalex publication_date 2023/12/21 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Several machine learning methods aim to learn or reason about complex physical systems. A common first-step towards reasoning is to infer system parameters from observations of its behavior. In this paper, we investigate the performance of Large Language Models (LLMs) at performing parameter inference in the context of physical systems. Our experiments suggest that they are not inherently suited to this task, even for simple systems. We propose a promising direction of exploration, which involves the use of physical simulators to augment the context of LLMs. We assess and compare the performance of different LLMs on a simple example with and without access to physical simulation.

Cited by

• Teaching Physical Awareness to LLMs through Sounds

Related

• LLMPhy: Parameter-Identifiable Physical Reasoning Combining Large Language Models and Physics Engines
• Using Machine Learning for Model Physics: an Overview
• Uncovering Emergent Physics Representations Learned In-Context by Large Language Models
• SimbaML: Connecting Mechanistic Models and Machine Learning with Augmented Data
• Using (Not-so) Large Language Models to Generate Simulation Models in a Formal DSL: A Study on Reaction Networks