Adaptations of AI models for querying the LandMatrix database in natural language

TL;DR

This paper explores how to adapt AI models, especially Large Language Models, to simplify querying the LandMatrix database in natural language, making data more accessible for policy and research use.

Contribution

It evaluates various LLM adaptation techniques like Prompt Engineering, RAG, and Agents for querying different database systems, providing a practical approach to improve data accessibility.

Findings

LLMs can effectively query LandMatrix data with proper adaptations.

Different adaptation methods vary in accuracy and usability.

The approach is reproducible and demonstrated online.

Abstract

The Land Matrix initiative (https://landmatrix.org) and its global observatory aim to provide reliable data on large-scale land acquisitions to inform debates and actions in sectors such as agriculture, extraction, or energy in low- and middle-income countries. Although these data are recognized in the academic world, they remain underutilized in public policy, mainly due to the complexity of access and exploitation, which requires technical expertise and a good understanding of the database schema. The objective of this work is to simplify access to data from different database systems. The methods proposed in this article are evaluated using data from the Land Matrix. This work presents various comparisons of Large Language Models (LLMs) as well as combinations of LLM adaptations (Prompt Engineering, RAG, Agents) to query different database systems (GraphQL and REST queries). The experiments are reproducible, and a demonstration is available online: https://github.com/tetis-nlp/landmatrix-graphql-python.