AI 中文总结
针对现有传感器-语言推理与信号关联弱、解释不可靠的问题，提出TRACE-TS框架，通过专家归因识别关键传感器区域并构建可追踪推理轨迹，在7个可穿戴基准上实现最优性能。
AI 中文摘要
可穿戴传感器能捕捉细粒度运动模式，支撑丰富的行为理解，但多数现有方法将这些信号简化为活动标签。近期基于大语言模型（LM）的方法会为传感器数据生成自然语言解释，但其推理与底层信号的关联薄弱，导致解释流畅却无法验证。我们提出TRACE-TS（基于归因证据的可追踪推理），这是针对可穿戴时间序列的结构化、信号基础推理框架。TRACE-TS利用专家分类器的归因识别显著的时空传感器区域，用这些区域构建带有明确证据来源的有向无环图（DAG）推理轨迹，并训练紧凑的语言模型，通过对传感器记忆标记的门控交叉注意力生成这些轨迹。推理阶段，适配后的模型会同时输出活动预测及其推理轨迹，无需归因计算或教师指导。我们提出语义节点匹配（SNM），一种作为评判者的大语言模型指标，可在观察、推理、综合层面诊断推理保真度，定位标准自然语言生成（NLG）指标遗漏的幻觉观察和断裂证据链。在7个可穿戴基准测试中，TRACE-TS在所有评估方法中取得最佳平均准确率和F1值（84.43%/81.24%），且在F1值上比最佳的基于大语言模型的基准方法高出17.96%。我们的代码可在该URL获取。
英文摘要
Wearable sensors capture fine-grained motion patterns that support rich behavioral understanding, yet most existing methods reduce these signals to activity labels. Recent LM-based approaches generate natural-language explanations for sensor data, but their reasoning is weakly grounded in the underlying signal, leading to fluent yet unverifiable explanations. We introduce TRACE-TS (Traceable Reasoning with Attribution-Grounded Evidence), a framework for structured and signal-grounded reasoning over wearable time series. TRACE-TS uses attribution from an expert classifier to identify salient spatio-temporal sensor regions, uses them to construct DAG reasoning traces with explicit evidence provenance, and trains a compact language model to generate these traces through gated cross-attention over sensor memory tokens. At inference, the adapted model jointly outputs the activity prediction and its reasoning trace, without requiring attribution computation or teacher guidance. We introduce Semantic Node Match(SNM), an LLM-as-judge metric that diagnoses reasoning fidelity at the observation, inference, and synthesis levels, localizing hallucinated observations and broken evidence chains missed by standard NLG metrics. Across seven wearable benchmarks, TRACE-TS achieves the best average accuracy and F1 among all evaluated methods (84.43%/81.24%), and outperforms the best LLM-based baseline by 17.96% in F1. Our code is available at https://github.com/SparshRastogi/TRACE-TS.
Comments24 pages, 9 figures, 24 tables
