{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/sensorllm-aligning-large-language-models-with","title":"SensorLLM: Human-Intuitive Alignment of Multivariate Sensor Data with LLMs for Activity Recognition","arxiv_id":"2410.10624","date":"2024-10-14","proceeding":null,"authors":["Zechen Li","Shohreh Deldari","Linyao Chen","Hao Xue","Flora D. Salim"],"abstract":"We introduce SensorLLM, a two-stage framework that enables Large Language Models (LLMs) to perform human activity recognition (HAR) from wearable sensor data. While LLMs excel at reasoning and generalization, they struggle with time-series inputs due to limited semantic context, numerical complexity, and sequence variability. To address these challenges, we construct SensorQA, a question-answering dataset of human-intuitive sensor-text pairs spanning diverse HAR scenarios. It supervises the Sensor-Language Alignment stage, where the model aligns sensor inputs with trend descriptions. Special tokens are introduced to mark channel boundaries. This alignment enables LLMs to interpret numerical patterns, channel-specific signals, and variable-length inputs--without requiring human annotation. In the subsequent Task-Aware Tuning stage, we adapt the model for multivariate HAR classification, achieving performance that matches or exceeds state-of-the-art methods. Our results show that, guided by human-intuitive alignment, SensorLLM becomes an effective sensor learner, reasoner, and classifier--generalizing across varied HAR settings and paving the way for foundation model research in time-series analysis.","url_abs":"https://arxiv.org/abs/2410.10624v3","url_pdf":"https://arxiv.org/pdf/2410.10624v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"sensorllm-aligning-large-language-models-with","repo_url":"https://github.com/zechenli03/sensorllm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"activity-recognition","task_name":"Activity Recognition"},{"task_slug":"descriptive","task_name":"Descriptive"},{"task_slug":"human-activity-recognition","task_name":"Human Activity Recognition"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"time-series-1","task_name":"Time Series"},{"task_slug":"time-series","task_name":"Time Series Analysis"}],"methods":[{"method_slug":"align","method_name":"ALIGN"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2410.10624","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}