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

arXiv: https://arxiv.org/abs/2505.17116 · HTML: https://mlsanity.com/paper/2505.17116/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 17 references that are in the map.
- First posted on arXiv 21 May 2025.

## Builds on (most cited first, 6 of 6)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Mixed Precision Training](https://mlsanity.com/paper/1710.03740/) (2017)
- [8-bit Optimizers via Block-wise Quantization](https://mlsanity.com/paper/2110.02861/) (2021)
- [Scaling Neural Machine Translation](https://mlsanity.com/paper/1806.00187/) (2018)
- [A RAG-Based Multi-Agent LLM System for Natural Hazard Resilience and Adaptation](https://mlsanity.com/paper/2504.17200/) (2025)

## Abstract (arXiv)

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.