Grounding Time Series in Language: Interpretable Reasoning with Large Language Models
Name
chen-l1ly-meng-eecs-2025-thesis.pdf
Description
Thesis PDF
Size
1.68 MB
Format
Adobe PDF
Checksum (MD5)
0e81781927e225d51c4e2f202bcf3f81
Author(s)
Chen, Lily
Advisor(s)
Liang, Paul
Date Issued
May 2025
Publisher
Massachusetts Institute of Technology
Abstract
Can large language models (LLMs) classify time-series data by reasoning like a domain expert—if given the right language? We propose a method that expresses statistical time-series features in natural language, enabling LLMs to perform classification with structured, interpretable reasoning. By grounding low-level signal descriptors in semantic context, our approach reframes time-series classification as a language-based reasoning task. We evaluate this method across 23 diverse univariate datasets spanning biomedical, sensor, and human activity domains. Despite requiring no fine-tuning, it achieves competitive accuracy compared to traditional and foundation model baselines. Our method also enables models to generate expert-style justifications, providing interpretable insights into their decision-making process. We present one of the first large-scale analyses of LLM reasoning over statistical time-series features, examining calibration, explanation structure, and reasoning behavior. This work highlights the potential of language native interfaces for interpretable and trustworthy time-series classification.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
In Copyright - Educational Use Permitted
Copyright retained by author(s)
Persistent DSpace Link
