Fine-Tuning Small Language Models (SLMs) for Autonomous Web-based Geographical Information Systems (AWebGIS)
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916884872429568 |
|---|---|
| author | Ashani, Mahdi Nazari Alesheikh, Ali Asghar Kazemi, Saba Kheirkhah, Kimya Mohammadi, Yasin Rezaie, Fatemeh Manafi, Amir Mahdi Zarkesh, Hedieh |
| author_facet | Ashani, Mahdi Nazari Alesheikh, Ali Asghar Kazemi, Saba Kheirkhah, Kimya Mohammadi, Yasin Rezaie, Fatemeh Manafi, Amir Mahdi Zarkesh, Hedieh |
| contents | Autonomous web-based geographical information systems (AWebGIS) aim to perform geospatial operations from natural language input, providing intuitive, intelligent, and hands-free interaction. However, most current solutions rely on cloud-based large language models (LLMs), which require continuous internet access and raise users' privacy and scalability issues due to centralized server processing. This study compares three approaches to enabling AWebGIS: (1) a fully-automated online method using cloud-based LLMs (e.g., Cohere); (2) a semi-automated offline method using classical machine learning classifiers such as support vector machine and random forest; and (3) a fully autonomous offline (client-side) method based on a fine-tuned small language model (SLM), specifically T5-small model, executed in the client's web browser. The third approach, which leverages SLMs, achieved the highest accuracy among all methods, with an exact matching accuracy of 0.93, Levenshtein similarity of 0.99, and recall-oriented understudy for gisting evaluation ROUGE-1 and ROUGE-L scores of 0.98. Crucially, this client-side computation strategy reduces the load on backend servers by offloading processing to the user's device, eliminating the need for server-based inference. These results highlight the feasibility of browser-executable models for AWebGIS solutions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_04846 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Fine-Tuning Small Language Models (SLMs) for Autonomous Web-based Geographical Information Systems (AWebGIS) Ashani, Mahdi Nazari Alesheikh, Ali Asghar Kazemi, Saba Kheirkhah, Kimya Mohammadi, Yasin Rezaie, Fatemeh Manafi, Amir Mahdi Zarkesh, Hedieh Artificial Intelligence Computation and Language Machine Learning Autonomous web-based geographical information systems (AWebGIS) aim to perform geospatial operations from natural language input, providing intuitive, intelligent, and hands-free interaction. However, most current solutions rely on cloud-based large language models (LLMs), which require continuous internet access and raise users' privacy and scalability issues due to centralized server processing. This study compares three approaches to enabling AWebGIS: (1) a fully-automated online method using cloud-based LLMs (e.g., Cohere); (2) a semi-automated offline method using classical machine learning classifiers such as support vector machine and random forest; and (3) a fully autonomous offline (client-side) method based on a fine-tuned small language model (SLM), specifically T5-small model, executed in the client's web browser. The third approach, which leverages SLMs, achieved the highest accuracy among all methods, with an exact matching accuracy of 0.93, Levenshtein similarity of 0.99, and recall-oriented understudy for gisting evaluation ROUGE-1 and ROUGE-L scores of 0.98. Crucially, this client-side computation strategy reduces the load on backend servers by offloading processing to the user's device, eliminating the need for server-based inference. These results highlight the feasibility of browser-executable models for AWebGIS solutions. |
| title | Fine-Tuning Small Language Models (SLMs) for Autonomous Web-based Geographical Information Systems (AWebGIS) |
| topic | Artificial Intelligence Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2508.04846 |