Language Models Still Struggle to Zero-shot Reason about Time Series

Mike Merrill, Mingtian Tan, Vinayak Gupta, Thomas Hartvigsen, Tim Althoff


Abstract
Time series are critical for decision-making in fields like finance and healthcare. Their importance has driven a recent influx of works passing time series into language models, leading to non-trivial forecasting on some datasets. But it remains unknown whether non-trivial forecasting implies that language models can reason about time series. To address this gap, we generate a first-of-its-kind evaluation framework for time series reasoning, including formal tasks and a corresponding dataset of multi-scale time series paired with text captions across ten domains. Using these data, we probe whether language models achieve three forms of reasoning: (1) Etiological Reasoning—given an input time series, can the language model identify the scenario that most likely created it? (2) Question Answering—can a language model answer factual questions about time series? (3) Context-Aided Forecasting–does highly relevant textual context improve a language model’s time series forecasts? We find that otherwise highly-capable language models demonstrate surprisingly limited time series reasoning: they score marginally above random on etiological and question answering tasks (up to 30 percentage points worse than humans) and show modest success in using context to improve forecasting. These weakness showcase that time series reasoning is an impactful, yet deeply underdeveloped direction for language model research. We also make our datasets public to support further research in this direction.
Anthology ID:
2024.findings-emnlp.201
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2024
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3512–3533
Language:
URL:
https://aclanthology.org/2024.findings-emnlp.201
DOI:
Bibkey:
Cite (ACL):
Mike Merrill, Mingtian Tan, Vinayak Gupta, Thomas Hartvigsen, and Tim Althoff. 2024. Language Models Still Struggle to Zero-shot Reason about Time Series. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 3512–3533, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Language Models Still Struggle to Zero-shot Reason about Time Series (Merrill et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-emnlp.201.pdf