Assessing ChatGPT’s legal reasoning in statutory land consolidation: The case of Cyprus
Journal
Land Use Policy
Date Issued
May 2026
Author(s)
DOI
10.1016/j.landusepol.2026.107960
Abstract
Land consolidation remains a cornerstone of rural development, but its implementation is often hindered by
complex statutory frameworks and lengthy procedures. In Cyprus, where land consolidation has historically
reduced fragmentation, the process faces new challenges amid declining agricultural importance and evolving
policy priorities such as climate change resilience, sustainable development, and urban land readjustment. At the
same time, artificial intelligence (AI) and large language models (LLMs) like ChatGPT are increasingly being
considered as tools to support legal and planning processes. This study provides the first systematic evaluation of
ChatGPT’s capacity to interpret and respond to legal questions derived from Cyprus’s Land Consolidation Law.
Using a corpus of 100 questions across four levels of legal complexity, responses were assessed with a rubric
measuring correctness, completeness, clarity, and interpretive depth. The results show strong performance in
basic factual and procedural questions (98% accuracy for Type 1), moderate reliability in procedural and hypothetical
reasoning (84% and 82% respectively), but significant decline in complex interpretive tasks (55% for
Type 4). These findings highlight both the potential and the limitations of LLMs in statutory interpretation: they
can provide accessible explanations and procedural guidance but cannot yet replace expert legal reasoning in
ambiguous or high-stakes cases. The study contributes to the emerging discourse on AI in land policy and rural
development, offering methodological insights for evaluating LLMs in domain-specific legal contexts and outlining implications for their responsible integration into planning, cadastral, and governance workflows.
complex statutory frameworks and lengthy procedures. In Cyprus, where land consolidation has historically
reduced fragmentation, the process faces new challenges amid declining agricultural importance and evolving
policy priorities such as climate change resilience, sustainable development, and urban land readjustment. At the
same time, artificial intelligence (AI) and large language models (LLMs) like ChatGPT are increasingly being
considered as tools to support legal and planning processes. This study provides the first systematic evaluation of
ChatGPT’s capacity to interpret and respond to legal questions derived from Cyprus’s Land Consolidation Law.
Using a corpus of 100 questions across four levels of legal complexity, responses were assessed with a rubric
measuring correctness, completeness, clarity, and interpretive depth. The results show strong performance in
basic factual and procedural questions (98% accuracy for Type 1), moderate reliability in procedural and hypothetical
reasoning (84% and 82% respectively), but significant decline in complex interpretive tasks (55% for
Type 4). These findings highlight both the potential and the limitations of LLMs in statutory interpretation: they
can provide accessible explanations and procedural guidance but cannot yet replace expert legal reasoning in
ambiguous or high-stakes cases. The study contributes to the emerging discourse on AI in land policy and rural
development, offering methodological insights for evaluating LLMs in domain-specific legal contexts and outlining implications for their responsible integration into planning, cadastral, and governance workflows.
File(s)![Thumbnail Image]()
Name
The published paper.pdf
Size
591.1 KB
Format
Adobe PDF
Checksum (MD5)
0b56d116e8e5a7cd04b586a45f937c27