Knowledge Distillation for LLM-Based Human Activity Recognition in Homes
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914248078131200 |
|---|---|
| author | Cumin, Julien Er-Rahmany, Oussama Chen, Xi |
| author_facet | Cumin, Julien Er-Rahmany, Oussama Chen, Xi |
| contents | Human Activity Recognition (HAR) is a central problem for context-aware applications, especially for smart homes and assisted living. A few very recent studies have shown that Large Language Models (LLMs) can be used for HAR at home, reaching high performance and addressing key challenges. In this paper, we provide new experimental results regarding the use of LLMs for HAR, on two state-of-the-art datasets. More specifically, we show how recognition performance evolves depending on the size of the LLM used. Moreover, we experiment on the use of knowledge distillation techniques to fine-tune smaller LLMs with HAR reasoning examples generated by larger LLMs. We show that such fine-tuned models can perform almost as well as the largest LLMs, while having 50 times less parameters. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_07469 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Knowledge Distillation for LLM-Based Human Activity Recognition in Homes Cumin, Julien Er-Rahmany, Oussama Chen, Xi Artificial Intelligence Human Activity Recognition (HAR) is a central problem for context-aware applications, especially for smart homes and assisted living. A few very recent studies have shown that Large Language Models (LLMs) can be used for HAR at home, reaching high performance and addressing key challenges. In this paper, we provide new experimental results regarding the use of LLMs for HAR, on two state-of-the-art datasets. More specifically, we show how recognition performance evolves depending on the size of the LLM used. Moreover, we experiment on the use of knowledge distillation techniques to fine-tune smaller LLMs with HAR reasoning examples generated by larger LLMs. We show that such fine-tuned models can perform almost as well as the largest LLMs, while having 50 times less parameters. |
| title | Knowledge Distillation for LLM-Based Human Activity Recognition in Homes |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2601.07469 |