Feasibility of Using a Multi-Agent LLM System to Correct Annotations and Support Low-Effort Activity Labeling
Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · 30.09.2026 · 10 (3) · 1-40
DOI: 10.1145/3831653 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, online erschienen am 30.09.2026. Verfasst von Ha Le und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 114 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science Foundation, National Institutes of Health.
Abstract (Originalsprache)
Accurate measurement of behaviors is critical for research in human-computer interaction, ubiquitous computing, and personal health informatics, because it underpins many health tracking and intervention systems. Most data collection studies, however, still rely on participants' self-reports and manual annotations, which often under- or over-estimate activity duration and type, and require substantial effort from researchers to clean and validate. An automated system that can combine passive sensing data with participants' self-reports might detect inconsistencies and suggest corrections. We introduce GLOSS4HAR, a multi-agent LLM-based system designed to mimic human sensemaking and assist researchers in cleaning and refining activity annotations. We demonstrate the potential of GLOSS4HAR in two key tasks: (1) correcting and reconciling participant self-annotations, and (2) triangulating passive sensing data with different forms of lightweight self-reports to generate accurate activity timelines. Our evaluation shows that GLOSS4HAR improves annotation quality by up to 9.9% in F1 score and can reconstruct activity timelines that align with human annotations at 75-92% F1. Based on our findings, we discuss the implications of our work for the next generation of activity annotation systems that might use human-AI collaboration.
Förderung
- National Science Foundation
- National Institutes of Health
Zitieren
APA
Le, H., Choube, A., Mishra, V., & Intille, S. S. (2026). Feasibility of Using a Multi-Agent LLM System to Correct Annotations and Support Low-Effort Activity Labeling. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, 10(3), 1-40. https://doi.org/10.1145/3831653
Vancouver
Le H, Choube A, Mishra V, Intille SS. Feasibility of Using a Multi-Agent LLM System to Correct Annotations and Support Low-Effort Activity Labeling. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies. 2026;10(3):1-40. doi:10.1145/3831653
BibTeX
@article{Le2026,
author = {Le, Ha and Choube, Akshat and Mishra, Varun and Intille, Stephen S.},
title = {Feasibility of Using a Multi-Agent LLM System to Correct Annotations and Support Low-Effort Activity Labeling},
journal = {Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies},
year = {2026},
volume = {10},
number = {3},
pages = {1--40},
doi = {10.1145/3831653}
}
EUVIMED