The study presents a novel approach to legal reasoning, integrating AI to navigate complexities and biases in global jurisprudence. It leverages advanced language models and a human-AI collaborative framework. The AI-based application, SHIRLEY, detects logical inconsistencies and biases across various legal decisions. The findings are compared using another AI-based application, SAM, to identify deviations in bias detections. The study also introduces a semi-automated arbitration process, which uses an AI arbitrator to critically evaluate biases and qualitative nuances identified by the AI applications. The aim is to uphold the integrity and fairness of legal judgments through a hybrid system of AI and human-based collaborative analysis.
Publication date: 7 Feb 2024
Project Page: N/A
Paper: https://arxiv.org/pdf/2402.04140
