When is it acceptable to break the rules? Knowledge representation of moral judgements based on empirical data
Name
10458_2024_Article_9667.pdf
Size
1.76 MB
Format
Adobe PDF
Checksum (MD5)
1514e1811a72c0d1fab2617e23e8e3ad
Author(s)
Awad, Edmond
Levine, Sydney
Loreggia, Andrea
Mattei, Nicholas
Rahwan, Iyad
Rossi, Francesca
Talamadupula, Kartik
Tenenbaum, Joshua
Kleiman-Weiner, Max
Date Issued
July 13, 2024
Journal
Autonomous Agents and Multi-Agent Systems
Publisher
Springer Science and Business Media LLC
Citation
Awad, E., Levine, S., Loreggia, A. et al. When is it acceptable to break the rules? Knowledge representation of moral judgements based on empirical data. Auton Agent Multi-Agent Syst 38, 35 (2024).
Version
Final published version
Abstract
Constraining the actions of AI systems is one promising way to ensure that these systems behave in a way that is morally acceptable to humans. But constraints alone come with drawbacks as in many AI systems, they are not flexible. If these constraints are too rigid, they can preclude actions that are actually acceptable in certain, contextual situations. Humans, on the other hand, can often decide when a simple and seemingly inflexible rule should actually be overridden based on the context. In this paper, we empirically investigate the way humans make these contextual moral judgements, with the goal of building AI systems that understand when to follow and when to override constraints. We propose a novel and general preference-based graphical model that captures a modification of standard dual process theories of moral judgment. We then detail the design, implementation, and results of a study of human participants who judge whether it is acceptable to break a well-established rule: no cutting in line. We then develop an instance of our model and compare its performance to that of standard machine learning approaches on the task of predicting the behavior of human participants in the study, showing that our preference-based approach more accurately captures the judgments of human decision-makers. It also provides a flexible method to model the relationship between variables for moral decision-making tasks that can be generalized to other settings.
MIT Department
Massachusetts Institute of Technology. Media Laboratory
Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences
Terms of Use
Creative Commons Attribution
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1007/s10458-024-09667-4
