Effects of Fairness and Explanation on Trust in Ethical AI

Angerschmid, Alessa; Theuermann, Kevin; Holzinger, Andreas; Chen, Fang; Zhou, Jianlong

doi:10.1007/978-3-031-14463-9_4

Cited by 4 publications

(3 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, the training data used for developing large language models often contain biases, and research has found that ChatGPT replicates gender biases in reference letters written for hypothetical employees ( Wan et al, 2023 ). Such disparities underscore the importance of aligning AI with human values, as perceived fairness significantly influences users’ trust in AI technologies ( Angerschmid et al, 2022 ).…”

Section: A Three-dimension Framework Of Trust In Aimentioning

confidence: 99%

“…The concepts of transparency and explainability are deeply interconnected; explainability, in particular, plays a crucial role in reducing users’ perceived risks associated with AI systems ( Qin et al, 2020 ). Additionally, providing reasonable explanations after AI errors can restore people’s trust in AI ( Angerschmid et al, 2022 ).…”

Section: A Three-dimension Framework Of Trust In Aimentioning

confidence: 99%

See 1 more Smart Citation

Developing trustworthy artificial intelligence: insights from research on interpersonal, human-automation, and human-AI trust

Li,

Wu,

Huang

et al. 2024

Front. Psychol.

View full text Add to dashboard Cite

The rapid advancement of artificial intelligence (AI) has impacted society in many aspects. Alongside this progress, concerns such as privacy violation, discriminatory bias, and safety risks have also surfaced, highlighting the need for the development of ethical, responsible, and socially beneficial AI. In response, the concept of trustworthy AI has gained prominence, and several guidelines for developing trustworthy AI have been proposed. Against this background, we demonstrate the significance of psychological research in identifying factors that contribute to the formation of trust in AI. Specifically, we review research findings on interpersonal, human-automation, and human-AI trust from the perspective of a three-dimension framework (i.e., the trustor, the trustee, and their interactive context). The framework synthesizes common factors related to trust formation and maintenance across different trust types. These factors point out the foundational requirements for building trustworthy AI and provide pivotal guidance for its development that also involves communication, education, and training for users. We conclude by discussing how the insights in trust research can help enhance AI’s trustworthiness and foster its adoption and application.

show abstract

Section: A Three-dimension Framework Of Trust In Aimentioning

confidence: 99%

Section: A Three-dimension Framework Of Trust In Aimentioning

confidence: 99%

Developing trustworthy artificial intelligence: insights from research on interpersonal, human-automation, and human-AI trust

Li,

Wu,

Huang

et al. 2024

Front. Psychol.

View full text Add to dashboard Cite

show abstract

“…In light of the ethical concern of deploying ML models in more real-world applications, the field of trustworthy ML has grown, which studies and pursues desirable qualities such as fairness, explainability, transparency, privacy and robustness (Varshney, 2019;Angerschmid et al, 2022). Both explainability and robustness may have the potential to promote reliability and trust, and can ensure that humans intelligence complements AI (Holzinger, 2021).…”

Section: Modulating and Manipulating Trustmentioning

confidence: 99%

Leveraging explanations in interactive machine learning: An overview

Teso

Alkan²,

Stammer

et al. 2023

Front. Artif. Intell.

View full text Add to dashboard Cite

Explanations have gained an increasing level of interest in the AI and Machine Learning (ML) communities in order to improve model transparency and allow users to form a mental model of a trained ML model. However, explanations can go beyond this one way communication as a mechanism to elicit user control, because once users understand, they can then provide feedback. The goal of this paper is to present an overview of research where explanations are combined with interactive capabilities as a mean to learn new models from scratch and to edit and debug existing ones. To this end, we draw a conceptual map of the state-of-the-art, grouping relevant approaches based on their intended purpose and on how they structure the interaction, highlighting similarities and differences between them. We also discuss open research issues and outline possible directions forward, with the hope of spurring further research on this blooming research topic.

show abstract