交通流预测在智能交通系统（ITS）中发挥核心作用，支撑实时决策、拥堵管理及长期规划。然而，现有诸多方法面临实际应用局限：多数时空模型依赖中心化数据训练、采用数值化表征，且可解释性有限；近期基于大语言模型（LLM）的方法虽提升了推理能力，但通常假设数据可集中获取，未能充分刻画真实交通系统固有的分布式与异构特性。为应对上述挑战，本研究提出 FedLLM（Federated LLM），一种面向可解释多步短期交通流预测（15–60 分钟）的隐私保护型分布式框架。该框架包含四项关键贡献：1）复合选择得分（CSS），一种数据驱动的高速公路路段选择机制，用以刻画不同交通区域间的结构多样性；2）面向交通领域适配的 LLM，经结构化交通提示（prompt）微调，该提示编码了空间、时间与统计上下文；3）FedLLM 框架本身，支持异构客户端间的协同训练，仅交换轻量级 LoRA 适配器参数；4）一种结构化提示表征，支持上下文推理与跨区域泛化。FedLLM 的设计使各客户端可在本地学习交通模式，同时通过高效参数交换参与全局模型构建，在降低通信开销的同时保障数据隐私，并适用于非独立同分布（non-IID）的交通数据场景。实验结果表明，FedLLM 在预测性能上优于中心化基线模型，并生成结构清晰、可解释的输出。

Traffic prediction plays a central role in intelligent transportation systems (ITS) by supporting real-time decision-making, congestion management, and long-term planning. However, many existing approaches face practical limitations. Most spatio-temporal models are trained on centralized data, rely on numerical representations, and offer limited explainability. Recent Large Language Model (LLM) methods improve reasoning capabilities but typically assume centralized data availability and do not fully capture the distributed and heterogeneous nature of real-world traffic systems. To address these challenges, this study proposes FedLLM (Federated LLM), a privacy-preserving and distributed framework for explainable multi-horizon short-term traffic flow prediction (15-60 minutes). The framework introduces four key contributions: 1) a Composite Selection Score (CSS) for data-driven freeway selection that captures structural diversity across traffic regions 2) a domain-adapted LLM fine-tuned on structured traffic prompts encoding spatial, temporal, and statistical context 3) FedLLM framework, that enables collaborative training across heterogeneous clients while exchanging only lightweight LoRA adapter parameters, 4) a structured prompt representation that supports contextual reasoning and cross-region generalization. The FedLLM design allows each client to learn from local traffic patterns while contributing to a shared global model through efficient parameter exchange, reducing communication overhead and keeping data private. This setup supports learning under non-IID traffic distributions. Experimental results show that FedLLM achieves improved predictive performance over centralized baselines, while producing structured and explainable outputs. These findings highlight the potential of combining FL with domain-adapted LLMs for scalable, privacy-aware, and explainable traffic prediction.