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.

Other difficult tasks, more generally, are how to obtain a robust performance in teamworks (Cohen and Levesque 1990); how to prevent agents from dropping their commitments; or better, how to regulate agents dropping their commitments to a joint action to not disrupt the common activity and preclude the common goal being achieved (Jennings 1995; Singh 1995; Kinny and Georgeff 1991). These tasks have now entered the MAS field's common knowledge. Other problems are perhaps less obvious. The Second International Conference on Multiagent Systems (ICMAS '96) Workshop on Norms, Obligations, and Conventions was held in Kyoto, Japan, from 10 to 13 December 1996. Participants included scientists from deontic logic, database framework, decision theory, agent architecture, cognitive modeling, and legal expert systems.