From Text to Structure: Using Large Language Models to Support the Development of Legal Expert Systems
This addresses the bottleneck of time-consuming manual encoding in developing transparent and explainable legal expert systems for laypeople, representing an incremental improvement.
The researchers tackled the problem of automating the extraction of structured representations from legislative text to support legal expert systems, finding that large language models like GPT-4 generated pathways with 60% rated as equivalent or better than manually created ones in a blind comparison.
Encoding legislative text in a formal representation is an important prerequisite to different tasks in the field of AI & Law. For example, rule-based expert systems focused on legislation can support laypeople in understanding how legislation applies to them and provide them with helpful context and information. However, the process of analyzing legislation and other sources to encode it in the desired formal representation can be time-consuming and represents a bottleneck in the development of such systems. Here, we investigate to what degree large language models (LLMs), such as GPT-4, are able to automatically extract structured representations from legislation. We use LLMs to create pathways from legislation, according to the JusticeBot methodology for legal decision support systems, evaluate the pathways and compare them to manually created pathways. The results are promising, with 60% of generated pathways being rated as equivalent or better than manually created ones in a blind comparison. The approach suggests a promising path to leverage the capabilities of LLMs to ease the costly development of systems based on symbolic approaches that are transparent and explainable.