Building Ethics into Artificial Intelligence

By Han Yu, Zhiqi Shen, Chunyan Miao, Cyril Leung, Victor R. Lesser, Qiang Yang. 2018

213 citations recorded by the source corpus.

As artificial intelligence (AI) systems become increasingly ubiquitous, the topic of AI governance for ethical decision-making by AI has captured public imagination. Within the AI research community, this topic remains less familiar to many researchers. In this paper, we complement existing surveys, which largely focused on the psychological, social and legal discussions of the topic, with an analysis of recent advances in technical solutions for AI governance. By reviewing publications in leading AI conferences including AAAI, AAMAS, ECAI and IJCAI, we propose a taxonomy which divides the field into four areas: 1) exploring ethical dilemmas; 2) individual ethical decision frameworks; 3) collective ethical decision frameworks; and 4) ethics in human-AI interactions. We highlight the intuitions and key techniques used in each approach, and discuss promising future research directions towards successful integration of ethical AI systems into human societies.

Subfields: Artificial Intelligence, Cognitive Neuroscience, Safety Research

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Cognitive Neuroscience

In Safety Research

Citations in the corpus

Ethical principles in machine learning and artificial intelligence: cases from the field and possible ways forward (2020, background): “While re ﬂ ections around the ethical implications of machines and automation deployment were already put forth in the ’ 50s and ’ 60s (Samuel, 1959; Wiener, 1988), the increasing use of AI in many ﬁ elds raises new important questions about its suitability (Yu et al., 2018).”
Bias in data‐driven artificial intelligence systems—An introductory survey (2020, background): “This paper complements existing surveys that either have a strong focus on machine ethics, such as Yu et al. (2018), study a specific subproblem, such as explaining black box models (Atzmueller, 2017; Guidotti et al., 2019), or focus in specific contexts, such as the Web (Baeza-Yates, 2018), by…”
Trustworthy Artificial Intelligence: A Review (2022, background): “This step deals with the amount of decision information and explanations given to different stakeholders [132, 188] and specifying if-else conditions provides guidelines for how the system should perform and be used [220, 222].”
Scruples: A Corpus of Community Ethical Judgments on 32, 000 Real-Life Anecdotes (2020, background): “Nonetheless, researchers have proposed a number of promising approaches (Yu et al. 2018).”
What to account for when accounting for algorithms: a systematic literature review on algorithmic accountability (2020, background): “Different fora can be interwoven, but each requires different kinds of explanations and justifications [cf. 21, 22, 142].”
FedVision: An Online Visual Object Detection Platform Powered by Federated Learning (2020, background): “We are also working on improving the explainability of models through visualization (Wei et al. 2019) in the platform in order to build trust with the users (Yu et al. 2018).”
Seven HCI Grand Challenges (2019, background): “Nevertheless, depending on how the explanations are used, a balance needs to be achieved in the level of details, because full transparency may be too overwhelming in certain cases, while not enough transparency may jeopardize human trust in AI (Chen et al., 2018; Yu et al., 2018).”
A Full Dive Into Realizing the Edge-Enabled Metaverse: Visions, Enabling Technologies, and Challenges (2022, background): “training is conducted on the labeled data stored on local devices [301]–[304].”