An official website of the United States government
Many real-life scenarios require humans to make difficult trade-offs: do we always follow all the traffic rules or do we violate the speed limit in an emergency? In general, how should we account for and balance the ethical values, safety recommendations, and societal norms, when we are trying to achieve a certain objective? To enable effective AI-human collaboration, we must equip AI agents with a model of how humans make such trade-offs in environments where there is not only a goal to be reached, but there are also ethical constraints to be considered and to possibly align with. These ethical constraints could be both deontological rules on actions that should not be performed, or also consequentialist policies that recommend avoiding reaching certain states of the world. Our purpose is to build AI agents that can mimic human behavior in these ethically constrained decision environments, with a long term research goal to use AI to help humans in making better moral judgments and actions. To this end, we propose a computational approach where competing objectives and ethical constraints are orchestrated through a method that leverages a cognitive model of human decision making, called multi-alternative decision field theory (MDFT). Using MDFT, we build an orchestrator, called MDFT-Orchestrator (MDFT-O), that is both general and flexible. We also show experimentally that MDFT-O both generates better decisions than using a heuristic that takes a weighted average of competing policies (WA-O), but also performs better in terms of mimicking human decisions as collected through Amazon Mechanical Turk (AMT). Our methodology is therefore able to faithfully model human decision in ethically constrained decision environments.
more »
« less
When is it acceptable to break the rules? Knowledge representation of moral judgements based on empirical data
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 standarddual processtheories 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.
more »
« less
- PAR ID:
- 10579706
- Publisher / Repository:
- Autonomous Agents and Multi-Agent Systems
- Date Published:
- Journal Name:
- Autonomous Agents and Multi-Agent Systems
- Volume:
- 38
- Issue:
- 2
- ISSN:
- 1387-2532
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Dominant approaches to the ethics of artificial intelligence (AI) systems have been mainly based on individualistic, rule-based ethical frameworks central to Western cultures. These approaches have encountered both philosophical and computational limitations. They often struggle to accommodate remarkably diverse, unstable, complex contexts of human-AI interactions. Recently there has been an increasing interest among philosophers and computer scientists in building a relational approach to the ethics of AI. This article engages with Daniel A. Bell and Pei Wang’s most recent book Just Hierarchy and explores how their theory of just hierarchy can be employed to develop a more systematic account for relational AI ethics. Bell and Wang’s theory of just hierarchy acknowledges that there are morally justified situations in which social relations are not equal. Just hierarchy can exist both between humans and between humans and machines such as AI systems. Therefore, a relational ethic for AI based on just hierarchy can include two theses: (i) AI systems should be considered merely as tools and their relations with humans are hierarchical (e.g. designing AI systems with lower moral standing than humans); and (ii) the moral assessment of AI systems should focus on whether they help us realize our rolebased moral obligations prescribed by our social relations with others (these relations often involve diverse forms of morally justified hierarchies in communities). Finally, this article will discuss the practical implications of such a relational ethic framework for designing socially integrated and ethically responsive AI systems.more » « less
-
Abstract AI assistance is readily available to humans in a variety of decision-making applications. In order to fully understand the efficacy of such joint decision-making, it is important to first understand the human’s reliance on AI. However, there is a disconnect between how joint decision-making is studied and how it is practiced in the real world. More often than not, researchers ask humans to provide independent decisions before they are shown AI assistance. This is done to make explicit the influence of AI assistance on the human’s decision. We develop a cognitive model that allows us to infer thelatentreliance strategy of humans on AI assistance without asking the human to make an independent decision. We validate the model’s predictions through two behavioral experiments. The first experiment follows aconcurrentparadigm where humans are shown AI assistance alongside the decision problem. The second experiment follows asequentialparadigm where humans provide an independent judgment on a decision problem before AI assistance is made available. The model’s predicted reliance strategies closely track the strategies employed by humans in the two experimental paradigms. Our model provides a principled way to infer reliance on AI-assistance and may be used to expand the scope of investigation on human-AI collaboration.more » « less
-
AI systems are often used to make or contribute to important decisions in a growing range of applications, including criminal justice, hiring, and medicine. Since these decisions impact human lives, it is important that the AI systems act in ways which align with human values. Techniques for preference modeling and social choice help researchers learn and aggregate peoples' preferences, which are used to guide AI behavior; thus, it is imperative that these learned preferences are accurate. These techniques often assume that people are willing to express strict preferences over alternatives; which is not true in practice. People are often indecisive, and especially so when their decision has moral implications. The philosophy and psychology literature shows that indecision is a measurable and nuanced behavior---and that there are several different reasons people are indecisive. This complicates the task of both learning and aggregating preferences, since most of the relevant literature makes restrictive assumptions on the meaning of indecision. We begin to close this gap by formalizing several mathematical indecision models based on theories from philosophy, psychology, and economics; these models can be used to describe (indecisive) agent decisions, both when they are allowed to express indecision and when they are not. We test these models using data collected from an online survey where participants choose how to (hypothetically) allocate organs to patients waiting for a transplant.more » « less
-
The increased integration of artificial intelligence (AI) technologies in human workflows has resulted in a new paradigm of AI-assisted decision making,in which an AI model provides decision recommendations while humans make the final decisions. To best support humans in decision making, it is critical to obtain a quantitative understanding of how humans interact with and rely on AI. Previous studies often model humans' reliance on AI as an analytical process, i.e., reliance decisions are made based on cost-benefit analysis. However, theoretical models in psychology suggest that the reliance decisions can often be driven by emotions like humans' trust in AI models. In this paper, we propose a hidden Markov model to capture the affective process underlying the human-AI interaction in AI-assisted decision making, by characterizing how decision makers adjust their trust in AI over time and make reliance decisions based on their trust. Evaluations on real human behavior data collected from human-subject experiments show that the proposed model outperforms various baselines in accurately predicting humans' reliance behavior in AI-assisted decision making. Based on the proposed model, we further provide insights into how humans' trust and reliance dynamics in AI-assisted decision making is influenced by contextual factors like decision stakes and their interaction experiences.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1007/s10458-024-09667-4
