TRACE-TS: Attribution-Grounded and Traceable Sensor-Language Reasoning for Human Activity Understanding

• URL: http://arxiv.org/abs/2608.00200v1
• Date: Fri, 31 Jul 2026 18:26:17 GMT
• Title: TRACE-TS: Attribution-Grounded and Traceable Sensor-Language Reasoning for Human Activity Understanding
• Abstract summary: We introduce TRACE-TS, a framework for structured signal-grounded reasoning over wearable time series.<n>At inference, the adapted model jointly computation activity prediction and its reasoning trace, without requiring attribution or teacher guidance.<n>Across seven wearable benchmarks, TRACE-TS achieves the best average accuracy and F1 among all evaluated methods.
• Score: 13.162821843671411
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• LogSemFuse: Semantic Evidence Fusion for Explainable Log Anomaly Detection [6.950497660953971]
  LogSemFuse is an evidence-guided plug-in framework that enhances existing backbone detectors without replacing their original pipelines.<n>We evaluate LogSemFuse on HDFS, BGL, and Liberty using DeepLog, LogAnomaly, LogBERT, and NeuralLog as backbones.
  arXiv  Detail & Related papers  (2026-07-03T20:50:07Z)
• The Regularizing Power of Language-Training Deepfake Detectors [57.529452351298495]
  Deepfake detection generally suffers from overfitting to low-level domain-specific artifacts.<n>We use a dual-encoder architecture, pairing a frozen specialist detector with a LoRA-tuned MLLM encoder.<n>We employ a reinforcement learning stage that encourages the model to generate descriptive reasoning before classifying.
  arXiv  Detail & Related papers  (2026-05-29T12:01:17Z)
• Heuristic-inspired Reasoning Priors Facilitate Data-Efficient Referring Object Detection [53.988759250627425]
  HeROD (Heuristic-inspired ROD) is a lightweight, model-agnostic framework that injects explicit, interpretable spatial and semantic reasonings.<n>HeROD consistently outperforms strong grounding baselines in scarcelabel regimes.
  arXiv  Detail & Related papers  (2026-03-25T10:33:22Z)
• Explainable Semantic Textual Similarity via Dissimilar Span Detection [53.32175252285023]
  We introduce the task of Dissimilar Span Detection (DSD), which aims to identify semantically differing spans between pairs of texts.<n>This can help users understand which particular words or tokens negatively affect the similarity score, or be used to improve performance in STS-dependent downstream tasks.
  arXiv  Detail & Related papers  (2026-03-22T11:32:31Z)
• From Indoor to Open World: Revealing the Spatial Reasoning Gap in MLLMs [65.04549036809557]
  We introduce a benchmark built from pedestrian-perspective videos captured with synchronized stereo cameras, LiDAR, and IMU/GPS sensors.<n>This dataset provides metrically precise 3D information, enabling the automatic generation of spatial reasoning questions.<n> Evaluations reveal that the performance gains observed in structured indoor benchmarks vanish in open-world settings.
  arXiv  Detail & Related papers  (2025-12-22T18:58:12Z)
• COMPASS: Context-Modulated PID Attention Steering System for Hallucination Mitigation [2.1521364454860525]
  We introduce a lightweight, interpretable control framework that embeds a model-based feedback loop directly within decoding.<n>We show that a PID controller dynamically modulates attention heads to maintain factual consistency without retraining or multi-pass decoding.
  arXiv  Detail & Related papers  (2025-11-05T05:30:28Z)
• Few Shot Semi-Supervised Learning for Abnormal Stop Detection from Sparse GPS Trajectories [9.895353254067894]
  Abnormal stop detection in intercity coach transportation is critical for ensuring passenger safety, operational reliability, and regulatory compliance.<n>Existing methods often assume dense sampling or regular movement patterns, limiting their applicability.<n>We propose a Sparsity-Aware (SAS) method that adaptively defines segment boundaries based on local spatial-temporal density.
  arXiv  Detail & Related papers  (2025-10-14T16:22:34Z)
• PSRT: Accelerating LRM-based Guard Models via Prefilled Safe Reasoning Traces [81.70980843006681]
  We introduce PSRT, a method that replaces the model's reasoning process with a Prefilled Safe Reasoning Trace.<n>PSRT prefills "safe reasoning virtual tokens" from a constructed dataset and learns over their continuous embeddings.<n>We evaluate PSRT on 7 models, 13 datasets, and 8 jailbreak methods.
  arXiv  Detail & Related papers  (2025-09-26T02:14:31Z)
• Do Cognitively Interpretable Reasoning Traces Improve LLM Performance? [15.970162088175593]
  Chain-of-Thought (CoT) traces generate intermediate reasoning traces before producing an answer.<n>A common but often implicit assumption is that CoT traces should be semantically meaningful and interpretable to the end user.<n>We investigate this question in the Open Book Question-Answering domain by supervised fine-tuning LLaMA and Qwen models.
  arXiv  Detail & Related papers  (2025-08-21T23:48:50Z)
• The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reasoning Models [69.798277882245]
  We introduce Unsupervised Prefix Fine-Tuning (UPFT) to enhance large language models' reasoning efficiency.<n>UPFT removes the need for labeled data or exhaustive sampling.<n> Experiments show that UPFT matches the performance of supervised methods.
  arXiv  Detail & Related papers  (2025-03-04T18:56:03Z)
• SensorLLM: Aligning Large Language Models with Motion Sensors for Human Activity Recognition [13.796942110105313]
  We introduce SensorLLM, a framework that enables Large Language Models (LLMs) to perform human activity recognition (HAR) from sensor time-series data.<n> SensorLLM addresses limitations through a Sensor-Language Alignment stage, where the model aligns sensor inputs with trend descriptions.<n>In the subsequent Task-Aware Tuning stage, we refine the model for HAR classification, achieving performance that matches or surpasses state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-10-14T15:30:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.