对比提示与微调在地理栅格数据上的表现，发现微调更优。

Comparative Evaluation of Prompting and Fine-Tuning for Applying Large Language Models to Grid-Structured Geospatial Data

• 用结构化提示让基础模型处理地理栅格数据
• 微调模型在时空推理任务上显著优于零样本提示
• 适合需要精准地理分析的科研与工程人员

本文对大型语言模型（LLMs）在解释网格结构地理空间数据方面进行了对比研究。通过结构化提示评估基础模型性能，并与在用户-助手交互数据集上微调的版本进行对比。结果表明，零样本提示存在局限性，而微调在结构化地理与时间推理任务中展现出明显优势。研究验证了针对特定地理数据场景进行微调的有效性，为地理信息智能处理提供了新思路。

原文摘要 · Abstract (English)

This paper presents a comparative study of large language models (LLMs) in interpreting grid-structured geospatial data. We evaluate the performance of a base model through structured prompting and contrast it with a fine-tuned variant trained on a dataset of user-assistant interactions. Our results highlight the strengths and limitations of zero-shot prompting and demonstrate the benefits of fine-tuning for structured geospatial and temporal reasoning.

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。