In this paper, we propose an LLM-Guided Exemplar Selection framework to address a key limitation in state-of-the-art Human Activity Recognition (HAR) methods: their reliance on large labeled datasets and purely geometric exemplar selection, which often fail to distinguish similar wearable sensor activities such as walking, walking upstairs, and walking downstairs. Our method incorporates semantic reasoning via an LLM-generated knowledge prior that captures feature importance, inter-class confusability, and exemplar budget multipliers, and uses it to guide exemplar scoring and selection. These priors are combined with margin-based validation cues, PageRank centrality, hubness penalization, and facility-location optimization to obtain a compact and informative set of exemplars. Evaluated on the UCI-HAR dataset under strict few-shot conditions, the framework achieves a macro F1-score of 88.78%, outperforming classical approaches such as random sampling, herding, and k-center. The results show that LLM-derived semantic priors, when integrated with structural and geometric cues, provide a stronger foundation for selecting representative sensor exemplars in few-shot wearable-sensor HAR.

翻译：本文提出一种LLM引导的范例选择框架，旨在解决当前最先进人体活动识别方法的关键局限：其对大规模标注数据集的依赖以及纯几何范例选择策略的不足——这类策略常难以区分相似的可穿戴传感器活动（如行走、上楼梯与下楼梯）。本方法通过LLM生成的知识先验引入语义推理机制，该先验捕获特征重要性、类间混淆度及范例预算乘数，并以此指导范例评分与选择。这些先验与基于间隔的验证线索、PageRank中心性、枢纽度惩罚及设施选址优化相结合，从而获得紧凑且信息丰富的范例集合。在UCI-HAR数据集上进行的严格少样本实验表明，该框架实现了88.78%的宏F1分数，优于随机采样、聚类中心选择及k中心点等传统方法。结果表明，LLM衍生的语义先验与结构几何线索结合后，能为少样本可穿戴传感器人体活动识别中代表性传感器范例的选择提供更坚实的基础。