Rationale-Grounded In-Context Learning for Time Series Reasoning with Multimodal Large Language Models

TL;DR

This paper introduces RationaleTS, a method that improves multimodal large language models' ability to reason about time series data by using rationale-guided in-context learning, leading to more principled reasoning.

Contribution

It proposes a novel rationale-grounded in-context learning approach with label-conditioned rationales and hybrid retrieval, enhancing time series reasoning in multimodal models.

Findings

RationaleTS outperforms existing methods on three time series reasoning tasks.

The approach demonstrates improved reasoning accuracy and efficiency.

Code will be released for reproducibility.

Abstract

The underperformance of existing multimodal large language models for time series reasoning lies in the absence of rationale priors that connect temporal observations to their downstream outcomes, which leads models to rely on superficial pattern matching rather than principled reasoning. We therefore propose the rationale-grounded in-context learning for time series reasoning, where rationales work as guiding reasoning units rather than post-hoc explanations, and develop the RationaleTS method. Specifically, we firstly induce label-conditioned rationales, composed of reasoning paths from observable evidence to the potential outcomes. Then, we design the hybrid retrieval by balancing temporal patterns and semantic contexts to retrieve correlated rationale priors for the final in-context inference on new samples. We conduct extensive experiments to demonstrate the effectiveness and efficiency of our proposed RationaleTS on three-domain time series reasoning tasks. We will release our code for reproduction.