GLOSS: Group of LLMs for Open-Ended Sensemaking of Passive Sensing Data for Health and Wellbeing
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908460159860736 |
|---|---|
| author | Choube, Akshat Le, Ha Li, Jiachen Ji, Kaixin Swain, Vedant Das Mishra, Varun |
| author_facet | Choube, Akshat Le, Ha Li, Jiachen Ji, Kaixin Swain, Vedant Das Mishra, Varun |
| contents | The ubiquitous presence of smartphones and wearables has enabled researchers to build prediction and detection models for various health and behavior outcomes using passive sensing data from these devices. Achieving a high-level, holistic understanding of an individual's behavior and context, however, remains a significant challenge. Due to the nature of passive sensing data, sensemaking -- the process of interpreting and extracting insights -- requires both domain knowledge and technical expertise, creating barriers for different stakeholders. Existing systems designed to support sensemaking are either not open-ended or cannot perform complex data triangulation. In this paper, we present a novel sensemaking system, Group of LLMs for Open-ended Sensemaking (GLOSS), capable of open-ended sensemaking and performing complex multimodal triangulation to derive insights. We demonstrate that GLOSS significantly outperforms the commonly used Retrieval-Augmented Generation (RAG) technique, achieving 87.93% accuracy and 66.19% consistency, compared to RAG's 29.31% accuracy and 52.85% consistency. Furthermore, we showcase the promise of GLOSS through four use cases inspired by prior and ongoing work in the UbiComp and HCI communities. Finally, we discuss the potential of GLOSS, its broader implications, and the limitations of our work. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_05461 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GLOSS: Group of LLMs for Open-Ended Sensemaking of Passive Sensing Data for Health and Wellbeing Choube, Akshat Le, Ha Li, Jiachen Ji, Kaixin Swain, Vedant Das Mishra, Varun Human-Computer Interaction The ubiquitous presence of smartphones and wearables has enabled researchers to build prediction and detection models for various health and behavior outcomes using passive sensing data from these devices. Achieving a high-level, holistic understanding of an individual's behavior and context, however, remains a significant challenge. Due to the nature of passive sensing data, sensemaking -- the process of interpreting and extracting insights -- requires both domain knowledge and technical expertise, creating barriers for different stakeholders. Existing systems designed to support sensemaking are either not open-ended or cannot perform complex data triangulation. In this paper, we present a novel sensemaking system, Group of LLMs for Open-ended Sensemaking (GLOSS), capable of open-ended sensemaking and performing complex multimodal triangulation to derive insights. We demonstrate that GLOSS significantly outperforms the commonly used Retrieval-Augmented Generation (RAG) technique, achieving 87.93% accuracy and 66.19% consistency, compared to RAG's 29.31% accuracy and 52.85% consistency. Furthermore, we showcase the promise of GLOSS through four use cases inspired by prior and ongoing work in the UbiComp and HCI communities. Finally, we discuss the potential of GLOSS, its broader implications, and the limitations of our work. |
| title | GLOSS: Group of LLMs for Open-Ended Sensemaking of Passive Sensing Data for Health and Wellbeing |
| topic | Human-Computer Interaction |
| url | https://arxiv.org/abs/2507.05461 |