Morality in AI. A plea to embed morality in LLM architectures and frameworks

TL;DR

This paper advocates for embedding moral understanding directly into the architecture of large language models using top-down design principles inspired by biological attention and philosophical theories, aiming to enhance ethical decision-making in AI.

Contribution

It introduces a novel framework that conceptualizes attention as a dynamic system mediating structure and processing, and proposes technical pathways for embedding morality into LLM architectures.

Findings

Attention as a dynamic mediating system

Pathways for embedding morality via training and architecture

Complementarity of architectural and external ethical methods

Abstract

Large language models (LLMs) increasingly mediate human decision-making and behaviour. Ensuring LLM processing of moral meaning therefore has become a critical challenge. Current approaches rely predominantly on bottom-up methods such as fine-tuning and reinforcement learning from human feedback. We propose a fundamentally different approach: embedding moral meaning processing directly into the architectural mechanisms and frameworks of transformer-based models through top-down design principles. We first sketch a framework that conceptualizes attention as a dynamic interface mediating between structure and processing, contrasting with existing linear attention frameworks in psychology. We start from established biological-artificial attention analogies in neural architecture design to improve cognitive processing. We extend this analysis to moral processing, using Iris Murdoch's theory of loving attention (sustained, just observation that enables moral transformation by reseeing others with clarity and compassion) to philosophically discuss functional analogies between human and LLM moral processing. We formulate and evaluate potentially promising technical operationalizations to embed morality in LLM architectures and frameworks. We acknowledge the limitations of our exploration and give three key contributions. (1) We conceptualize attention as a dynamic system mechanism mediating between structure and processing. (2) Drawing on the Murdoch notion of loving attention, we outline technical pathways for embedding morality in LLMs, through modified training objectives, runtime weight adjustments, and architectural refinements to attention. (3) We argue that integrating morality into architectures and frameworks complements external, constraint-based methods. We conclude with a call for collaboration between transformer designers and philosophers engaged in AI ethics.