Expanding Explainability: Towards Social Transparency in AI systems

By Upol Ehsan, Q. Liao, Michael J. Muller, Mark O. Riedl, Justin D. Weisz. International Conference on Human Factors in Computing Systems, 2021

589 citations recorded by the source corpus.

As AI-powered systems increasingly mediate consequential decision-making, their explainability is critical for end-users to take informed and accountable actions. Explanations in human-human interactions are socially-situated. AI systems are often socio-organizationally embedded. However, Explainable AI (XAI) approaches have been predominantly algorithm-centered. We take a developmental step towards socially-situated XAI by introducing and exploring Social Transparency (ST), a sociotechnically informed perspective that incorporates the socio-organizational context into explaining AI-mediated decision-making. To explore ST conceptually, we conducted interviews with 29 AI users and practitioners grounded in a speculative design scenario. We suggested constitutive design elements of ST and developed a conceptual framework to unpack ST’s effect and implications at the technical, decision-making, and organizational level. The framework showcases how ST can potentially calibrate trust in AI, improve decision-making, facilitate organizational collective actions, and cultivate holistic explainability. Our work contributes to the discourse of Human-Centered XAI by expanding the design space of XAI.

Subfields: Artificial Intelligence, Computer Science Applications, Safety Research

View Paper: https://www.semanticscholar.org/paper/c8965761083d80ff762ce76c08df92d66e01f37d

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 Computer Science Applications

In Safety Research

Citations in the corpus

Data Cards: Purposeful and Transparent Dataset Documentation for Responsible AI (2022, background): “This reflects real world constraints of the diversity of goals, workflows, and backgrounds of individual stakeholders participating in the life cycles of datasets and artificial intelligence (AI) systems [11, 13, 14].”
Human-Centered Explainable AI (XAI): From Algorithms to User Experiences (2021, methodology): “Motivated by this sociotechnical perspective, with collaborators we proposed the concept of social transparency–making visible the social-organizational factors that govern the use of AI systems [31].”
Explanations Can Reduce Overreliance on AI Systems During Decision-Making (2022, background): “Ecological Validity: Selecting maze solving trade s off some ecological validity compared to other tasks, as few human-XAI tasks outside of the lab will include solving mazes, but a rich literature in cognitive psychology and cognitive science involves solving puzzles of this sort (e.g., [2, 60]).”
Should ChatGPT be Biased? Challenges and Risks of Bias in Large Language Models (2023, background): “When users and regulators can see that developers are taking steps to ensure the fairness and equity of their models, they may be more likely to trust and adopt these technologies [92, 93].”
Survey of Explainable AI Techniques in Healthcare (2023, background): “Radiologists also want to know the opinions of others when using AI tools for diagnosis [98].”
Design Principles for Generative AI Applications (2024, background): “For example, one set of papers examined requirements for explainable AI (XAI) and human-centered explainable AI (HCXAI) through experimental and heuristic methods [43, 98, 166], motivating “ex-plainability” as an important high-level concept.”
How Platform-User Power Relations Shape Algorithmic Accountability: A Case Study of Instant Loan Platforms and Financially Stressed Users in India (2022, background): “Prior work calls for aligning transparency with user needs [42, 75].”