Modelling Competing Legal Arguments using Bayesian Model Comparison and Averaging

TL;DR

This paper introduces a novel Bayesian model comparison and averaging method for legal arguments, allowing multiple independent models to be evaluated and combined based on their factual support, accommodating conflicting narratives.

Contribution

It presents a new approach to compare and average independent Bayesian models of legal arguments without requiring variable or causal consistency.

Findings

Models more disconfirmed by facts receive lower weights

The approach enables rational aggregation of conflicting legal arguments

Allows plurality of arguments with a single, coherent judgment

Abstract

Bayesian models of legal arguments generally aim to produce a single integrated model, combining each of the legal arguments under consideration. This combined approach implicitly assumes that variables and their relationships can be represented without any contradiction or misalignment, and in a way that makes sense with respect to the competing argument narratives. This paper describes a novel approach to compare and 'average' Bayesian models of legal arguments that have been built independently and with no attempt to make them consistent in terms of variables, causal assumptions or parametrisation. The approach involves assessing whether competing models of legal arguments are explained or predict facts uncovered before or during the trial process. Those models that are more heavily disconfirmed by the facts are given lower weight, as model plausibility measures, in the Bayesian model comparison and averaging framework adopted. In this way a plurality of arguments is allowed yet a single judgement based on all arguments is possible and rational.