PATRA: Pattern-Aware Alignment and Balanced Reasoning for Time Series Question Answering
This work aims to improve time series question answering for users who need to interpret complex time series data, representing an incremental improvement in this domain.
This paper addresses limitations in LLM-based time series question answering by proposing PATRA, a model that extracts trend and seasonality patterns for deep alignment and uses a task-aware balanced reward to improve reasoning across tasks. PATRA outperforms strong baselines across diverse TSQA tasks.
Time series reasoning demands both the perception of complex dynamics and logical depth. However, existing LLM-based approaches exhibit two limitations: they often treat time series merely as text or images, failing to capture the patterns like trends and seasonalities needed to answer specific questions; and when trained on a mix of simple and complex tasks, simpler objectives often dominate the learning process, hindering the development of deep reasoning capabilities. To address these limitations, we propose the Pattern-Aware Alignment and Balanced Reasoning model (PATRA), introducing a pattern-aware mechanism that extracts trend and seasonality patterns from time series to achieve deep alignment. Furthermore, we design a task-aware balanced reward to harmonize learning across tasks of varying difficulty, incentivizing the generation of coherent Chains of Thought. Extensive experiments show that PATRA outperforms strong baselines across diverse Time Series Question Answering (TSQA) tasks, demonstrating superior cross-modal understanding and reasoning capability.