Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Social, Legal, Ethical, Empathetic, and Cultural Rules: Compilation and Reasoning (Extended Version)

Nicolas Troquard, Martina De Sanctis, Paola Inverardi, Patrizio Pelliccione, Gian Luca Scoccia

TL;DR

This work addresses the challenge of enforcing human-context norms in AI by formalizing SLEEC rules (social, legal, ethical, empathetic, and cultural) through a linguistically grounded translation to classical logic. It demonstrates that the rules can be compiled into a uniform logical form whose semantics enable verification, consistency checks, and deployment via SAT solvers and logic programming frameworks (ASP, PROLOG). The authors establish a general compilation pattern with a quadratic size growth, show coNP-complete entailment in general (with Horn-like fragments solvable in PTIME), and illustrate practical reasoning on a running nursing-home example across propositional logic, ASP, and PROLOG. The results provide a pragmatic, tool-compatible pathway to design norm-conformant AI systems and inform further developments in normative multi-agent reasoning and ethical AI deployment.

Abstract

The rise of AI-based and autonomous systems is raising concerns and apprehension due to potential negative repercussions stemming from their behavior or decisions. These systems must be designed to comply with the human contexts in which they will operate. To this extent, Townsend et al. (2022) introduce the concept of SLEEC (social, legal, ethical, empathetic, or cultural) rules that aim to facilitate the formulation, verification, and enforcement of the rules AI-based and autonomous systems should obey. They lay out a methodology to elicit them and to let philosophers, lawyers, domain experts, and others to formulate them in natural language. To enable their effective use in AI systems, it is necessary to translate these rules systematically into a formal language that supports automated reasoning. In this study, we first conduct a linguistic analysis of the SLEEC rules pattern, which justifies the translation of SLEEC rules into classical logic. Then we investigate the computational complexity of reasoning about SLEEC rules and show how logical programming frameworks can be employed to implement SLEEC rules in practical scenarios. The result is a readily applicable strategy for implementing AI systems that conform to norms expressed as SLEEC rules.

Social, Legal, Ethical, Empathetic, and Cultural Rules: Compilation and Reasoning (Extended Version)

TL;DR

This work addresses the challenge of enforcing human-context norms in AI by formalizing SLEEC rules (social, legal, ethical, empathetic, and cultural) through a linguistically grounded translation to classical logic. It demonstrates that the rules can be compiled into a uniform logical form whose semantics enable verification, consistency checks, and deployment via SAT solvers and logic programming frameworks (ASP, PROLOG). The authors establish a general compilation pattern with a quadratic size growth, show coNP-complete entailment in general (with Horn-like fragments solvable in PTIME), and illustrate practical reasoning on a running nursing-home example across propositional logic, ASP, and PROLOG. The results provide a pragmatic, tool-compatible pathway to design norm-conformant AI systems and inform further developments in normative multi-agent reasoning and ethical AI deployment.

Abstract

The rise of AI-based and autonomous systems is raising concerns and apprehension due to potential negative repercussions stemming from their behavior or decisions. These systems must be designed to comply with the human contexts in which they will operate. To this extent, Townsend et al. (2022) introduce the concept of SLEEC (social, legal, ethical, empathetic, or cultural) rules that aim to facilitate the formulation, verification, and enforcement of the rules AI-based and autonomous systems should obey. They lay out a methodology to elicit them and to let philosophers, lawyers, domain experts, and others to formulate them in natural language. To enable their effective use in AI systems, it is necessary to translate these rules systematically into a formal language that supports automated reasoning. In this study, we first conduct a linguistic analysis of the SLEEC rules pattern, which justifies the translation of SLEEC rules into classical logic. Then we investigate the computational complexity of reasoning about SLEEC rules and show how logical programming frameworks can be employed to implement SLEEC rules in practical scenarios. The result is a readily applicable strategy for implementing AI systems that conform to norms expressed as SLEEC rules.
Paper Structure (24 sections, 2 theorems, 13 equations, 1 figure)

This paper contains 24 sections, 2 theorems, 13 equations, 1 figure.

Table of Contents

  1. Introduction
  2. Compilation and Reasoning.
  3. Outline.
  4. Elements of Logic and Logic Programming
  5. Propositional Logic
  6. Logic Programming
  7. Unless... In Which Case...
  8. 'Unless' as XOR
  9. The Logical Form of 'Unless'
  10. Unless... in Which Case...
  11. Identifying the Pieces of Information in SLEEC Rules
  12. Disambiguation of Other Words: Tell and Tell
  13. Determining the Pieces of Information in the Domain
  14. Compilation of SLEEC Rules Into Logic
  15. General Pattern for SLEEC Rules
  16. ...and 9 more sections

Key Result

Proposition 1

Let $AP$ be a set of propositional variables. Deciding whether an obligation $\phi$ (more generally, any propositional statement over $AP$) is entailed by a set $\Gamma$ of SLEEC rules is coNP-complete, even if the terms $C_0, \ldots C_n$ and $O_0, \ldots O_n$ in every rule are restricted to be lite

Figures (1)

  • Figure 1: SLEEC-compliant AI systems.

Theorems & Definitions (15)

  • Example 1
  • Example 1: continue
  • Example 1: continue
  • Definition 1
  • Example 2
  • Definition 2
  • Example 3
  • Definition 3
  • Example 4
  • Definition 4
  • ...and 5 more