Research Papers 论文研究 4h ago Updated 2h ago 更新于 2小时前 45

TRACE-TS: Attribution-Grounded and Traceable Sensor-Language Reasoning for Human Activity Understanding TRACE-TS:面向人类活动理解的归因 grounded 且可追溯的传感器-语言推理

TRACE-TS introduces a framework for structured, signal-grounded reasoning over wearable sensor time series, addressing the weak grounding problem in existing LM-based approaches The method uses attribution from an expert classifier to identify salient spatio-temporal sensor regions and constructs DAG reasoning traces with explicit evidence provenance A compact language model is trained via gated cross-attention over sensor memory tokens to generate these reasoning traces, with inference requirin 提出TRACE-TS框架,实现可穿戴传感器数据的结构化、可追溯的传感器-语言联合推理 利用专家分类器归因识别显著时空传感器区域,构建具有明确证据溯源的DAG推理轨迹 引入Semantic Node Match (SNM)指标,在观察、推理和综合层面诊断推理保真度,定位标准NLG指标遗漏的幻觉 在七个可穿戴基准测试中取得最佳平均准确率84.43%和F1 81.24%,超越最佳LLM基线17.96%

58
Hot 热度
72
Quality 质量
65
Impact 影响力

Analysis 深度分析

TL;DR

  • TRACE-TS introduces a framework for structured, signal-grounded reasoning over wearable sensor time series, addressing the weak grounding problem in existing LM-based approaches
  • The method uses attribution from an expert classifier to identify salient spatio-temporal sensor regions and constructs DAG reasoning traces with explicit evidence provenance
  • A compact language model is trained via gated cross-attention over sensor memory tokens to generate these reasoning traces, with inference requiring no attribution computation or teacher guidance
  • Semantic Node Match (SNM), an LLM-as-judge metric, is proposed to diagnose reasoning fidelity at observation, inference, and synthesis levels, localizing hallucinations missed by standard NLG metrics
  • TRACE-TS achieves best average accuracy (84.43%) and F1 (81.24%) across seven wearable benchmarks, outperforming the best LLM-based baseline by 17.96% in F1

Why It Matters

This work addresses a critical gap in AI-driven human activity recognition: the tendency of language models to produce fluent but unverifiable explanations that lack grounding in actual sensor data. For AI practitioners building wearable-based health or behavioral monitoring systems, TRACE-TS provides a practical pathway to generate trustworthy, traceable reasoning that can be audited and validated against raw sensor signals.

Technical Details

  • TRACE-TS employs attribution-based identification of salient spatio-temporal regions in wearable sensor data, using an expert classifier to pinpoint which sensor signals and time windows are most relevant to a given activity
  • DAG (Directed Acyclic Graph) reasoning traces are constructed with explicit evidence provenance, creating structured chains of observation → inference → synthesis that can be audited
  • A compact language model is trained through gated cross-attention mechanisms over sensor memory tokens, enabling joint output of activity predictions and reasoning traces at inference without requiring attribution computation or distillation from a teacher model
  • Semantic Node Match (SNM) is an LLM-as-judge evaluation metric that operates at three fidelity levels—observation, inference, and synthesis—to detect hallucinated observations and broken evidence chains that standard NLG metrics fail to catch
  • Evaluated across seven wearable benchmarks, achieving 84.43% accuracy and 81.24% F1, with a 17.96% F1 improvement over the best LLM-based baseline

Industry Insight

  • The integration of attribution-based grounding with language model reasoning sets a new standard for explainable AI in wearable and IoT applications, where trust and verifiability are paramount for clinical or safety-critical deployments
  • The SNM metric offers a reusable evaluation framework for any domain where LLM-generated reasoning must be grounded in structured data, potentially extending beyond wearable sensors to medical imaging, industrial monitoring, and autonomous systems
  • The teacher-free inference design—eliminating the need for attribution computation at test time—makes TRACE-TS practically deployable in resource-constrained edge environments, bridging the gap between research prototypes and real-world wearable AI products

TL;DR

  • 提出TRACE-TS框架,实现可穿戴传感器数据的结构化、可追溯的传感器-语言联合推理
  • 利用专家分类器归因识别显著时空传感器区域,构建具有明确证据溯源的DAG推理轨迹
  • 引入Semantic Node Match (SNM)指标,在观察、推理和综合层面诊断推理保真度,定位标准NLG指标遗漏的幻觉
  • 在七个可穿戴基准测试中取得最佳平均准确率84.43%和F1 81.24%,超越最佳LLM基线17.96%

为什么值得看

本文解决了可穿戴传感器数据分析中长期存在的"推理与信号脱节"问题,为可解释AI在时序信号领域的应用提供了新思路。提出的SNM评估指标填补了现有NLG指标无法诊断推理链断裂的空白,对医疗、健康监测等高风险场景具有重要参考价值。

技术解析

  • TRACE-TS框架核心:使用专家分类器的归因分析识别传感器数据中的显著时空区域,将这些区域作为证据节点构建有向无环图(DAG)推理轨迹,实现从原始信号到自然语言解释的显式溯源。
  • 模型架构:采用紧凑语言模型,通过门控交叉注意力机制在传感器记忆token上进行推理轨迹生成。推理阶段无需归因计算或教师指导,模型联合输出活动预测和推理轨迹。
  • SNM评估指标:提出LLM-as-judge方法,在观察(observation)、推理(inference)和综合(synthesis)三个层级诊断推理保真度,能够精准定位标准NLG指标无法检测的幻觉观察和断裂证据链。
  • 实验结果:在七个可穿戴基准测试上,TRACE-TS达到84.43%准确率和81.24% F1,显著优于所有对比方法,其中F1较最佳LLM基线提升17.96个百分点。

行业启示

  • 可穿戴设备与健康监测领域对AI可解释性需求迫切,TRACE-TS的"信号接地推理"范式为构建可信AI系统提供了可复用的技术路径。
  • 多模态AI正从"预测准确"向"推理可验证"演进,DAG结构化推理轨迹的设计思路可推广至其他时序信号理解任务(如工业监控、自动驾驶)。
  • 评估体系需超越传统NLG指标,SNM的三级诊断框架为AI推理质量评估树立了新标准,建议行业在关键应用中引入类似细粒度评估机制。

Disclaimer: The above content is generated by AI and is for reference only. 免责声明:以上内容由 AI 生成,仅供参考。

LLM 大模型 Multimodal 多模态 Research 科学研究 Evaluation 评测