English

Improving Zero-shot ADL Recognition with Large Language Models through Event-based Context and Confidence

Computer Vision and Pattern Recognition 2026-01-14 v1 Distributed, Parallel, and Cluster Computing

Abstract

Unobtrusive sensor-based recognition of Activities of Daily Living (ADLs) in smart homes by processing data collected from IoT sensing devices supports applications such as healthcare, safety, and energy management. Recent zero-shot methods based on Large Language Models (LLMs) have the advantage of removing the reliance on labeled ADL sensor data. However, existing approaches rely on time-based segmentation, which is poorly aligned with the contextual reasoning capabilities of LLMs. Moreover, existing approaches lack methods for estimating prediction confidence. This paper proposes to improve zero-shot ADL recognition with event-based segmentation and a novel method for estimating prediction confidence. Our experimental evaluation shows that event-based segmentation consistently outperforms time-based LLM approaches on complex, realistic datasets and surpasses supervised data-driven methods, even with relatively small LLMs (e.g., Gemma 3 27B). The proposed confidence measure effectively distinguishes correct from incorrect predictions.

Keywords

Cite

@article{arxiv.2601.08241,
  title  = {Improving Zero-shot ADL Recognition with Large Language Models through Event-based Context and Confidence},
  author = {Michele Fiori and Gabriele Civitarese and Marco Colussi and Claudio Bettini},
  journal= {arXiv preprint arXiv:2601.08241},
  year   = {2026}
}
R2 v1 2026-07-01T09:02:10.026Z