Fine-tuning Small Language Models (SLMs) for autonomous web-based geographical information systems (AWebGIS)

Autonomous web-based geographical information systems (AWebGIS) aim to perform geospatial operations from natural language input, providing intuitive, intelligent, and hands-free interaction directly within a Web environment. However, most current solutions rely on cloud-based large language models (LLMs), which suffer from centralized processing issues like high operational costs and limited user privacy. This study explores an alternative architectural direction by deploying fine-tuned Small Language Models (SLMs) directly inside the user’s web browser to support AWebGIS. We compare two distinct approaches: (i) a method utilizing a cloud-based LLM (DeepSeek Chat V3.1), and (ii) a method based on three fine-tuned browser-executable SLMs – T5-small, T5-efficient-mini, and T5-efficient-tiny – executed entirely on the user’s device via WebAssembly/WebGPU. The T5-small model (60 M parameters, 155 MB) achieved an Exact Match Accuracy (EMA) of 0.82, Levenshtein Similarity (LS) of 0.96, ROUGE-1, and ROUGE-L scores of 0.95. Even the smallest model, T5-efficient-tiny (16 M parameters, 59 MB), maintained a functional EMA of 0.56. This browser-native, on-device strategy reduces the computational load on cloud servers, eliminates the need for large infrastructures to host LLMs, avoids token-based operational costs, and enhances user privacy. These results demonstrate the feasibility of leveraging highly compressed, browser-executable SLMs for developing cost-efficient, installation-free, and decentralized AWebGIS. Very small Google T5-based Small Language Model (SLM) variants can equal or outperform much larger cloud-based LLMs for sentence-to-action conversion in GIS workflows, enabling cost-efficient Autonomous Web-based GIS (AWebGIS) by removing token-based pricing and the need for large-scale server infrastructures. Lightweight, task-specific, and browser-executable SLMs enable cross-platform, browser-native AWebGIS by mapping natural language instructions directly to predefined geospatial operations, while leveraging client-side computing power instead of centralized cloud resources. A decentralized, on-device AWebGIS architecture minimizes reliance on centralized cloud platforms and large data centers, supporting resilient, privacy-aware, and scalable geospatial systems.