用小模型在浏览器端实现智能地理信息操作，既快又保护隐私。
Fine-Tuning Small Language Models (SLMs) for Autonomous Web-based Geographical Information Systems (AWebGIS)
- 在浏览器里直接运行微调后的小语言模型，实现离线地理操作。
- 准确率93%，相似度达0.99，效果接近云端大模型。
- 适合注重隐私、低延迟的本地化地理信息应用开发者。
自主式基于网络的地理信息系统（AWebGIS）旨在通过自然语言输入完成空间操作，实现直观、智能、无需手动交互的体验。然而，现有方案多依赖云端大型语言模型（LLMs），需持续联网，引发隐私与可扩展性问题。本研究对比三种方法：(1) 使用云模型（如Cohere）的全自动在线方案；(2) 基于传统机器学习分类器（如SVM、随机森林）的半自动离线方案；(3) 基于微调小语言模型（如T5-small）的全自主离线方案，直接在客户端浏览器执行。结果表明，第三种方案在准确性上最优，精确匹配率达0.93，莱文斯坦相似度为0.99，ROUGE-1和ROUGE-L得分均为0.98。该策略将计算负载移至用户设备，无需服务器推理，显著降低后端压力。研究验证了浏览器内执行模型在AWebGIS中的可行性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。