A Normative Intermediate Representation for ASP-Based Compliance Reasoning
2026-06-03 • Artificial Intelligence
Artificial IntelligenceLogic in Computer Science
AI summaryⓘ
The authors introduce MONIR, a new way to represent rules for automated compliance checking using ASP (Answer Set Programming). They design MONIR to work in stages and support extra features like time-based rules and external functions. They apply their approach to Chinese ADAS (Advanced Driver Assistance Systems) regulations using help from large language models. Their experiments test how well the approach extracts information and how efficiently it solves problems incrementally.
MONIRAnswer Set Programmingcompliance reasoningtemporal rulesexternal functionsstable-model semanticsADAS regulationslarge language modelsincremental solvingoperational semantics
Authors
Yangfan Wu, Huanyu Yang, Jianmin Ji
Abstract
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.