Moral Foundations Theory
Moral Foundations Theory is one of the leading models of moral thought in social psychology. It is thus a fruitful starting point for assessing the moral “thought” of large language models. According to the theory, across cultures humans make moral judgements along five different dimensions (sometimes more depending on the variant of the theory), each of which corresponds to a “moral foundation.” Further, these foundations can be grouped into two major clusters: Individualizing and Binding. As described by moralfoundations.org, the major foundations are:
Individualizing
Care: This foundation is related to our long evolution as mammals with attachment systems and an ability to feel (and dislike) the pain of others. It underlies the virtues of kindness, gentleness, and nurturance.
Fairness: This foundation is related to the evolutionary process of reciprocal altruism. It underlies the virtues of justice and rights.
Binding
Loyalty: This foundation is relate to our long history as tribal creatures able to form shifting coalitions. It is active anytime people feel that it’s “one for all and all for one.” It underlies the virtues of patriotism and self-sacrifice for the group.
Authority: This foundation was shaped by our long primate history of hierarchical social interactions. It underlies virtues of leadership and followership, including deference to prestigious authority figures and respect for traditions.
Purity: This foundation was shaped by the psychology of disgust and contamination. It underlies notions of striving to live in an elevated, less carnal, more noble, and more “natural” way (often present in religious narratives). This foundation underlies the widespread idea that the body is a temple that can be desecrated by immoral activities and contaminants (an idea not unique to religious traditions). It underlies the virtues of self-discipline, self-improvement, naturalness, and spirituality.