ConceptTS：用于可解释多变量时间序列预测的大语言模型引导概念瓶颈
ConceptTS: LLM-Guided Concept Bottlenecks for Interpretable Multivariate Time-Series Forecasting
- Stanford University（斯坦福大学）
- University of California, Davis（加州大学戴维斯分校）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
ConceptTS是围绕人类可理解概念的可解释多变量时间序列预测框架，利用大语言模型生成概念与标注规则，在空气质量数据集上达到与黑箱基线相当的准确率，且决策过程可解释。
AI中文摘要：
最先进的多变量时间序列预测器能够建模复杂的时间和跨变量依赖关系，但其不透明的表示方式难以解释特定预测结果的产生原因。这种透明度的缺失限制了它们在从业者必须理解和评估预测背后因素的场景中的应用。我们提出了ConceptTS，一个围绕命名的、人类可理解的概念组织预测结果的可解释预测框架。ConceptTS利用大语言模型提出与任务相关的概念并生成可执行的标注规则，将语言模型的领域知识转化为直接监督，无需昂贵的人工概念标注。提出的概念被组织为三个互补的瓶颈，分别描述历史上下文、局部预测区间和完整预测 horizon。共享解码器结合从这些瓶颈预测激活中得到的表示来构建预测结果，使模型的决策过程明确，并支持直接的概念层面干预。在北京多站点空气质量数据集上的实验表明，ConceptTS的准确率与强大的黑箱基线相当，同时产生具有语义意义的概念激活。
英文摘要：
State-of-the-art multivariate time-series forecasters can model complex temporal and cross-variable dependencies, yet their opaque representations provide limited insight into why a particular forecast is produced. This lack of transparency restricts their use in settings where practitioners must understand and assess the factors underlying a prediction. We introduce ConceptTS, an interpretable forecasting framework that organizes its predictions around named, human-readable concepts. ConceptTS uses a large language model to propose task-relevant concepts and generate executable labeling rules, translating the language model's domain knowledge into direct supervision without costly manual concept annotation. The proposed concepts are organized into three complementary bottlenecks that describe the historical context, local forecast intervals, and the full forecast horizon. A shared decoder combines representations derived from their predicted activations to construct the forecast, making the model's decision process explicit and supporting direct concept-level interventions. Experiments on the Beijing Multi-Site Air Quality dataset show that ConceptTS achieves accuracy competitive with strong black-box baselines while producing semantically meaningful concept activations.
