Modelling and Explaining Legal Case-based Reasoners through Classifiers

TL;DR

This paper integrates factor-based case reasoning with logical classifier models to analyze legal precedents, providing formal representations and insights into reasoning processes in AI & Law.

Contribution

It combines modal logic-based classifiers with factor-based case reasoning, offering formal reformulations and new analytical tools for legal AI systems.

Findings

Reformulation of Horty's case bases in modal logic language

Representation results linking case-based reasoning and classifiers

Analysis of reasoning and preferences using classifier concepts

Abstract

This paper brings together two lines of research: factor-based models of case-based reasoning (CBR) and the logical specification of classifiers. Logical approaches to classifiers capture the connection between features and outcomes in classifier systems. Factor-based reasoning is a popular approach to reasoning by precedent in AI & Law. Horty (2011) has developed the factor-based models of precedent into a theory of precedential constraint. In this paper we combine the modal logic approach (binary-input classifier, BLC) to classifiers and their explanations given by Liu & Lorini (2021) with Horty's account of factor-based CBR, since both a classifier and CBR map sets of features to decisions or classifications. We reformulate case bases of Horty in the language of BCL, and give several representation results. Furthermore, we show how notions of CBR, e.g. reason, preference between reasons, can be analyzed by notions of classifier system.