Current legislation requires contracts to be written clearly and concisely. However, many contracts remain ambiguous and challenging for readers to understand. Advancements in natural language analysis using statistical and Large Language Models (LLMs) are improving the process of clarity verification by reducing the time needed for the overall process. In this paper, we investigate the potential of LLMs, such as ChatGPT and Giuri-Matrix, against existing statistical tools for natural language clarity checks. Results suggest the adaptability of traditional LLMs in verifying contractual clarity and providing suggestions for improvement of submitted contracts.
On exploiting LLMs and statis tical methods for testing contractual clarity in legal contracts
Ilaria Amelia Caggiano;Christian Esposito;Lucilla Gatt
2025-01-01
Abstract
Current legislation requires contracts to be written clearly and concisely. However, many contracts remain ambiguous and challenging for readers to understand. Advancements in natural language analysis using statistical and Large Language Models (LLMs) are improving the process of clarity verification by reducing the time needed for the overall process. In this paper, we investigate the potential of LLMs, such as ChatGPT and Giuri-Matrix, against existing statistical tools for natural language clarity checks. Results suggest the adaptability of traditional LLMs in verifying contractual clarity and providing suggestions for improvement of submitted contracts.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
