Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Causal Semantic Alignment for LLM-based Time Series Forecasting

About

Recent advances in Large Language Models (LLMs) have opened new possibilities for time series forecasting by enabling alignment between temporal patterns and pretrained word embeddings. However, most LLM-based methods overlook the heterogeneous nature of time series, where dynamic fluctuations and invariant semantics are entangled. This entanglement introduces spurious correlations during the alignment, as dynamic components act as confounders by simultaneously influencing invariant components and the resulting aligned embeddings. To address this issue, a variable-level alignment framework CVAformer is proposed. CVAformer explicitly disentangles each variable into invariant and dynamic components just before alignment, and applies causal intervention to mitigate the confounding effect of the dynamics. To better support variable-level alignment, CVAformer replaces the standard causal attention in LLMs with a non-causal attention mechanism that captures interactions among variables at each time step. Extensive experiments across long-term, short-term, few-shot, and zero-shot forecasting settings indicate that CVAformer matches or exceeds state-of-the-art performance on most datasets, and in some cases achieves notably better accuracy. Experimental results validate the effectiveness of variable-level alignment and dynamic disentanglement in CVAformer, offering a new perspective for LLM-based time series tasks.

Kexuan Zhang, Xiaobei Zou, Cesare Alippi, Gary G. Yen, Yang Tang• 2026

Related benchmarks

TaskDatasetResultRank
Long-term time-series forecastingETTh1
MAE0.388
600
Long-term time-series forecastingWeather
MSE0.16
527
Long-term time-series forecastingETTm2
MSE0.171
479
Long-term time-series forecastingETTh2
MSE0.281
474
Long-term time-series forecastingETTm1
MSE0.311
463
Long-term time-series forecastingTraffic
MSE0.401
433
Long-term time-series forecastingElectricity
MSE0.14
27
Showing 7 of 7 rows

Other info

Follow for update