MOJO: Multi-LLM Optimised Joint Objective - Generative Artificial Intelligence for Multi-Criteria Decision Analysis Framework

This study introduces the Multi-LLM Optimised Joint Objective (MOJO), a novel generative artificial intelligence (Gen-AI) driven multi-criteria decision analysis (MCDA) framework. MOJO uniquely integrates human expertise with multiple large language models (LLMs) to address limitations in traditional MCDA approaches. The information fusion framework combines risk-adjusted utility scoring, performance equilibrium, and reliability scoring, producing consensus-driven rankings that effectively account for uncertainty and non-linear risk preferences. Grounded in principles from prospect theory and utility theory, MOJO captures complex behavioural factors such as loss aversion and probability distortion. An ensemble of LLM outputs automates MCDA tasks, enhanced by systematic bias correction to reduce cognitive load and improve transparency. MOJO also incorporates a comprehensive illustrative case study evaluating treatments for Inflammatory Bowel Disease (IBD), demonstrating its applicability to complex scenarios involving clinical, operational, and ethical criteria. Results from validation experiments involving multiple LLMs and decision-makers across diverse scenarios highlight MOJO's robustness, reliability, and transparency, demonstrating its significant potential in high-stakes fields such as healthcare, engineering, and public policy.