SysCaps: Language Interfaces for Simulation Surrogates of Complex Systems

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Emami, Patrick, Li, Zhaonan, Sinha, Saumya, Nguyen, Truc
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915249087578112
author Emami, Patrick
Li, Zhaonan
Sinha, Saumya
Nguyen, Truc
author_facet Emami, Patrick
Li, Zhaonan
Sinha, Saumya
Nguyen, Truc
contents Surrogate models are used to predict the behavior of complex energy systems that are too expensive to simulate with traditional numerical methods. Our work introduces the use of language descriptions, which we call ``system captions'' or SysCaps, to interface with such surrogates. We argue that interacting with surrogates through text, particularly natural language, makes these models more accessible for both experts and non-experts. We introduce a lightweight multimodal text and timeseries regression model and a training pipeline that uses large language models (LLMs) to synthesize high-quality captions from simulation metadata. Our experiments on two real-world simulators of buildings and wind farms show that our SysCaps-augmented surrogates have better accuracy on held-out systems than traditional methods while enjoying new generalization abilities, such as handling semantically related descriptions of the same test system. Additional experiments also highlight the potential of SysCaps to unlock language-driven design space exploration and to regularize training through prompt augmentation.
format Preprint
id arxiv_https___arxiv_org_abs_2405_19653
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SysCaps: Language Interfaces for Simulation Surrogates of Complex Systems
Emami, Patrick
Li, Zhaonan
Sinha, Saumya
Nguyen, Truc
Machine Learning
Computation and Language
Systems and Control
Surrogate models are used to predict the behavior of complex energy systems that are too expensive to simulate with traditional numerical methods. Our work introduces the use of language descriptions, which we call ``system captions'' or SysCaps, to interface with such surrogates. We argue that interacting with surrogates through text, particularly natural language, makes these models more accessible for both experts and non-experts. We introduce a lightweight multimodal text and timeseries regression model and a training pipeline that uses large language models (LLMs) to synthesize high-quality captions from simulation metadata. Our experiments on two real-world simulators of buildings and wind farms show that our SysCaps-augmented surrogates have better accuracy on held-out systems than traditional methods while enjoying new generalization abilities, such as handling semantically related descriptions of the same test system. Additional experiments also highlight the potential of SysCaps to unlock language-driven design space exploration and to regularize training through prompt augmentation.
title SysCaps: Language Interfaces for Simulation Surrogates of Complex Systems
topic Machine Learning
Computation and Language
Systems and Control
url https://arxiv.org/abs/2405.19653