Explanations, Fairness, and Appropriate Reliance in Human-AI Decision-Making
Top Cited Papers
Open Access
- 11 May 2024
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 1-18
Abstract
In this work, we study the effects of feature-based explanations on distributive fairness of AI-assisted decisions, specifically focusing on the task of predicting occupations from short textual bios. We also investigate how any effects are mediated by humans’ fairness perceptions and their reliance on AI recommendations. Our findings show that explanations influence fairness perceptions, which, in turn, relate to humans’ tendency to adhere to AI recommendations. However, we see that such explanations do not enable humans to discern correct and incorrect AI recommendations. Instead, we show that they may affect reliance irrespective of the correctness of AI recommendations. Depending on which features an explanation highlights, this can foster or hinder distributive fairness: when explanations highlight features that are task-irrelevant and evidently associated with the sensitive attribute, this prompts overrides that counter AI recommendations that align with gender stereotypes. Meanwhile, if explanations appear task-relevant, this induces reliance behavior that reinforces stereotype-aligned errors. These results imply that feature-based explanations are not a reliable mechanism to improve distributive fairness.Keywords
All Related Versions
This publication has 102 references indexed in Scilit:
- The perils and pitfalls of explainable AI: Strategies for explaining algorithmic decision-makingGovernment Information Quarterly, 2022
- Fairness, explainability and in-between: understanding the impact of different explanation methods on non-expert users’ perceptions of fairness toward an algorithmic systemEthics and Information Technology, 2022
- What to expect from opening up ‘black boxes’? Comparing perceptions of justice between human and automated agentsComputers in Human Behavior, 2021
- What do we want from Explainable Artificial Intelligence (XAI)? – A stakeholder perspective on XAI and a conceptual model guiding interdisciplinary XAI researchArtificial Intelligence, 2021
- Evaluating XAI: A comparison of rule-based and example-based explanationsArtificial Intelligence, 2021
- Human-Centered Explainable AI: Towards a Reflective Sociotechnical Approach2020
- How do fairness definitions fare? Testing public attitudes towards three algorithmic definitions of fairness in loan allocationsArtificial Intelligence, 2020
- LimeOut: An Ensemble Approach to Improve Process Fairness2020
- Role of fairness, accountability, and transparency in algorithmic affordanceComputers in Human Behavior, 2019
- The Use of Cronbach’s Alpha When Developing and Reporting Research Instruments in Science EducationResearch in Science Education, 2017