Traffic forecasting is pivotal for intelligent transportation systems, where accurate and interpretable predictions can significantly enhance operational efficiency and safety. A key challenge stems from the heterogeneity of traffic conditions across diverse locations, leading to highly varied traffic data distributions. Large language models (LLMs) show exceptional promise for few-shot learning in such dynamic and data-sparse scenarios. However, existing LLM-based solutions often rely on prompt-tuning, which can struggle to fully capture complex graph relationships and spatiotemporal dependencies-thereby limiting adaptability and interpretability in real-world traffic networks. We address these gaps by introducing Strada-LLM, a novel multivariate probabilistic forecasting LLM that explicitly models both temporal and spatial traffic patterns. By incorporating proximal traffic information as covariates, Strada-LLM more effectively captures local variations and outperforms prompt-based existing LLMs. To further enhance adaptability, we propose a lightweight distribution-derived strategy for domain adaptation, enabling parameter-efficient model updates when encountering new data distributions or altered network topologies-even under few-shot constraints. Empirical evaluations on spatio-temporal transportation datasets demonstrate that Strada-LLM consistently surpasses state-of-the-art LLM-driven and traditional GNN-based predictors. Specifically, it improves long-term forecasting by 17% in RMSE error and 16% more efficiency. Moreover, it maintains robust performance across different LLM backbones with minimal degradation, making it a versatile and powerful solution for real-world traffic prediction tasks.

翻译：交通预测对于智能交通系统至关重要，准确且可解释的预测能显著提升运营效率与安全性。核心挑战源于不同地点交通状况的异质性，导致交通数据分布高度多变。大语言模型（LLMs）在此类动态且数据稀疏的场景中展现出卓越的小样本学习潜力。然而，现有基于LLM的解决方案通常依赖提示调优，难以充分捕捉复杂的图关系与时空依赖性——这限制了模型在实际交通网络中的适应性与可解释性。为弥补这些不足，我们提出Strada-LLM，一种新颖的多变量概率预测LLM，显式建模时空交通模式。通过将邻近交通信息作为协变量纳入，Strada-LLM更有效地捕捉局部变化，并超越基于提示的现有LLMs。为进一步增强适应性，我们提出一种轻量级的分布驱动域适应策略，使模型在遇到新数据分布或变化的网络拓扑时（即使在小样本约束下）能实现参数高效的更新。在时空交通数据集上的实证评估表明，Strada-LLM持续优于最先进的LLM驱动及传统基于GNN的预测方法。具体而言，其在长期预测中降低17%的RMSE误差并提升16%的效率。此外，该模型在不同LLM骨干网络上均保持稳健性能且性能衰减极小，使其成为现实世界交通预测任务中通用且强大的解决方案。