A Normative Intermediate Representation for ASP-Based Compliance Reasoning
For researchers and practitioners in automated compliance checking, this work provides a structured framework to bridge natural language regulations and executable compliance reasoning, though it is an incremental step combining existing techniques.
The paper proposes MONIR, a normative intermediate representation for ASP-based compliance reasoning, and instantiates it on Chinese ADAS regulations. Experiments show that the LLM-assisted pipeline achieves high extraction quality, and modular/incremental ASP solving improves efficiency.
We propose MONIR, a Modalized-Output Normative Intermediate Representation for ASP-based compliance reasoning. Its core fragment has a staged operational semantics, while MONIR-ASP provides an executable compilation and extensions for external functions, temporal rules, and stable-model reasoning. We instantiate the framework on Chinese ADAS regulations and standards with an LLM-assisted pipeline. Experiments evaluate extraction quality and the efficiency of modular and incremental ASP solving.