PulseAugur
EN
LIVE 23:51:07

New representation aids AI compliance reasoning with ASP

Researchers have introduced MONIR, a new intermediate representation designed for compliance reasoning using Answer Set Programming (ASP). This framework, MONIR-ASP, includes an executable compilation and extensions for advanced features like temporal rules and external functions. The system was tested on Chinese regulations for Advanced Driver-Assistance Systems (ADAS), utilizing an LLM-assisted pipeline to evaluate extraction quality and solving efficiency. AI

IMPACT This framework could streamline the process of ensuring AI systems adhere to complex regulatory requirements.

RANK_REASON The cluster contains a research paper detailing a new technical framework for AI compliance reasoning.

Read on arXiv cs.AI →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

New representation aids AI compliance reasoning with ASP

COVERAGE [2]

  1. arXiv cs.AI TIER_1 English(EN) · Yangfan Wu, Huanyu Yang, Jianmin Ji ·

    A Normative Intermediate Representation for ASP-Based Compliance Reasoning

    arXiv:2606.04619v1 Announce Type: new 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 f…

  2. arXiv cs.AI TIER_1 English(EN) · Jianmin Ji ·

    A Normative Intermediate Representation for ASP-Based Compliance Reasoning

    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 stabl…