Rethinking Machine Ethics -- Can LLMs Perform Moral Reasoning through the Lens of Moral Theories?
This work addresses the need for explainable and theory-grounded ethical AI systems, offering a novel approach to moral reasoning that moves beyond crowd-sourced data, though it is incremental in applying existing theories to language models.
The paper tackles the problem of making moral judgments in AI by proposing a top-down framework that steers language models to perform moral reasoning using established moral theories, demonstrating its effectiveness on theory-derived datasets and analyzing alignment with existing morality datasets.
Making moral judgments is an essential step toward developing ethical AI systems. Prevalent approaches are mostly implemented in a bottom-up manner, which uses a large set of annotated data to train models based on crowd-sourced opinions about morality. These approaches have been criticized for overgeneralizing the moral stances of a limited group of annotators and lacking explainability. This work proposes a flexible top-down framework to steer (Large) Language Models (LMs) to perform moral reasoning with well-established moral theories from interdisciplinary research. The theory-guided top-down framework can incorporate various moral theories. Our experiments demonstrate the effectiveness of the proposed framework on datasets derived from moral theories. Furthermore, we show the alignment between different moral theories and existing morality datasets. Our analysis exhibits the potential and flaws in existing resources (models and datasets) in developing explainable moral judgment-making systems.