Scenarios and Recommendations for Ethical Interpretive AI
This work tackles the problem of making AI more human-centered and ethically robust, though it is incremental as it focuses on data collection and analysis rather than a new method.
The paper addresses the challenge of enabling AI systems to perform human-like interpretive reasoning when faced with ambiguous ethical rules, by collecting a dataset of ethical rules and scenarios to analyze and provide practical recommendations.
Artificially intelligent systems, given a set of non-trivial ethical rules to follow, will inevitably be faced with scenarios which call into question the scope of those rules. In such cases, human reasoners typically will engage in interpretive reasoning, where interpretive arguments are used to support or attack claims that some rule should be understood a certain way. Artificially intelligent reasoners, however, currently lack the ability to carry out human-like interpretive reasoning, and we argue that bridging this gulf is of tremendous importance to human-centered AI. In order to better understand how future artificial reasoners capable of human-like interpretive reasoning must be developed, we have collected a dataset of ethical rules, scenarios designed to invoke interpretive reasoning, and interpretations of those scenarios. We perform a qualitative analysis of our dataset, and summarize our findings in the form of practical recommendations.