Comparative Evaluation of Prompting and Fine-Tuning for Applying Large Language Models to Grid-Structured Geospatial Data
This addresses the problem of applying LLMs to geospatial data for researchers and practitioners, but it is incremental as it compares existing methods.
The paper compared prompting and fine-tuning of large language models for interpreting grid-structured geospatial data, finding that fine-tuning improved structured reasoning while zero-shot prompting had limitations.
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.