Papers
Topics
Authors
Recent
Search
2000 character limit reached

Conceptualizing the Relationship between AI Explanations and User Agency

Published 5 Dec 2023 in cs.HC and cs.CY | (2312.03193v1)

Abstract: We grapple with the question: How, for whom and why should explainable artificial intelligence (XAI) aim to support the user goal of agency? In particular, we analyze the relationship between agency and explanations through a user-centric lens through case studies and thought experiments. We find that explanation serves as one of several possible first steps for agency by allowing the user convert forethought to outcome in a more effective manner in future interactions. Also, we observe that XAI systems might better cater to laypersons, particularly "tinkerers", when combining explanations and user control, so they can make meaningful changes.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (50)
  1. ACM. 2018. ACM Code of Ethics and Professional Conduct. (2018). https://www.acm.org/code-of-ethics
  2. Living Documents: Designing for User Agency over Automated Text Summarization. In CHI Conference on Human Factors in Computing Systems Extended Abstracts. 1–6.
  3. Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI. Information fusion 58 (2020), 82–115.
  4. Albert Bandura. 1982. Self-efficacy mechanism in human agency. American psychologist 37, 2 (1982), 122.
  5. Albert Bandura. 1996a. Reflections on human agency: Part I. Constructivism in the Human Sciences 1, 2 (1996), 3.
  6. Albert Bandura. 1996b. Reflections on human agency: Part II. Constructivism in the Human Sciences 1, 3/4 (1996), 5.
  7. Network dissection: Quantifying interpretability of deep visual representations. In Proceedings of the IEEE conference on computer vision and pattern recognition. 6541–6549.
  8. Understanding the role of individual units in a deep neural network. Proceedings of the National Academy of Sciences 117, 48 (2020), 30071–30078.
  9. GenderMag: A method for evaluating software’s gender inclusiveness. Interacting with Computers 28, 6 (2016), 760–787.
  10. Dan Calacci and Alex Pentland. 2022. Bargaining with the Black-Box: Designing and Deploying Worker-Centric Tools to Audit Algorithmic Management. Proc. ACM Hum.-Comput. Interact. 6, CSCW2, Article 428 (nov 2022), 24 pages. DOI:http://dx.doi.org/10.1145/3570601 
  11. Timothy Day and Jichen Zhu. 2017. Agency informing techniques: Communicating player agency in interactive narratives. In Proceedings of the 12th International Conference on the Foundations of Digital Games. 1–4.
  12. After-Action Review for AI (AAR/AI). ACM Trans. Interact. Intell. Syst. 11, 3–4, Article 29 (sep 2021), 35 pages. DOI:http://dx.doi.org/10.1145/3453173 
  13. Explainable artificial intelligence: A survey. In 2018 41st International convention on information and communication technology, electronics and microelectronics (MIPRO). IEEE, 0210–0215.
  14. John J Dudley and Per Ola Kristensson. 2018. A review of user interface design for interactive machine learning. ACM Transactions on Interactive Intelligent Systems (TiiS) 8, 2 (2018), 1–37.
  15. Expanding explainability: Towards social transparency in ai systems. In Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems. 1–19.
  16. Explainable artificial intelligence for education and training. The Journal of Defense Modeling and Simulation 19, 2 (2022), 133–144.
  17. GDPR. 2018. European Union General Data Protection Regulation, Article 15 - “Right of access by the data subject”. (2018). http://www.privacy-regulation.eu/en/article-15-right-of-access-by-the-data-subject-GDPR.htm Accessed: 1/16/2019.
  18. Home Video Editing Made Easy-Balancing Automation and User Control.. In INTERACT, Vol. 1. 464–471.
  19. Michael Goller and Christian Harteis. 2017. Human agency at work: Towards a clarification and operationalisation of the concept. In Agency at work. Springer, 85–103.
  20. Factual and counterfactual explanations for black box decision making. IEEE Intelligent Systems 34, 6 (2019), 14–23.
  21. Harold Hotelling. 1929. Stability in Competition. The Economic Journal 39, 153 (1929), 41–57. http://www.jstor.org/stable/2224214
  22. White House. 2022. Blueprint for an AI Bill of Rights. (2022). https://www.whitehouse.gov/ostp/ai-bill-of-rights/ Last accessed: 10/13/22.
  23. Incorporating user control in automated interactive scheduling systems. In Proceedings of the 8th ACM Conference on Designing Interactive Systems. 306–309.
  24. Catie Keck. 2019. DoorDash tip-skimming scheme prompts class action lawsuit seeking all those tips that didn’t go to drivers. (Jul 2019). https://gizmodo.com/doordash-tip-skimming-scheme-prompts-clash-action-lawsu-1836820630
  25. Frank C Keil. 2006. Explanation and understanding. Annual review of psychology 57 (2006), 227.
  26. Finding AI’s faults with AAR/AI: An empirical study. ACM Transactions on Interactive Intelligent Systems (TiiS) 12, 1 (2022), 1–33.
  27. Principles of explanatory debugging to personalize interactive machine learning. In Proceedings of the 20th international conference on intelligent user interfaces. 126–137.
  28. Selective Explanations: Leveraging Human Input to Align Explainable AI. arXiv preprint arXiv:2301.09656 (2023).
  29. Questioning the AI: informing design practices for explainable AI user experiences. In Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems. 1–15.
  30. Janeen D Loehr. 2022. The sense of agency in joint action: An integrative review. Psychonomic Bulletin & Review (2022), 1–29.
  31. Esther MacCallum-Stewart and Justin Parsler. 2007. Illusory agency in vampire: The masquerade–Bloodlines. Dichtung Digital. Journal für Kunst und Kultur digitaler Medien 9, 1 (2007), 1–17.
  32. Explaining explanations in AI. In Proceedings of the conference on fairness, accountability, and transparency. 279–288.
  33. Andy Newman. 2019. Doordash changes tipping model after uproar from customers. (Jul 2019). https://www.nytimes.com/2019/07/24/nyregion/doordash-tip-policy.html?action=click& module=Intentional& pgtype=Article
  34. Martin J. Osborne. 2004. An introduction to game theory. Oxford Univ. Press, New York, NY [u.a.]. http://gso.gbv.de/DB=2.1/CMD?ACT=SRCHA&SRT=YOP&IKT=1016&TRM=ppn+369342747&sourceid=fbw_bibsonomy
  35. " Why should i trust you?" Explaining the predictions of any classifier. In Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining. 1135–1144.
  36. Automation Accuracy Is Good, but High Controllability May Be Better. In Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems (CHI ’19). Association for Computing Machinery, New York, NY, USA, 1–8. DOI:http://dx.doi.org/10.1145/3290605.3300750 
  37. Appropriate Reliance on AI Advice: Conceptualization and the Effect of Explanations. In Proceedings of the 28th International Conference on Intelligent User Interfaces (IUI ’23). Association for Computing Machinery, New York, NY, USA, 410–422. DOI:http://dx.doi.org/10.1145/3581641.3584066 
  38. Ben Shneiderman. 2020. Human-centered artificial intelligence: Reliable, safe & trustworthy. International Journal of Human–Computer Interaction 36, 6 (2020), 495–504.
  39. Grand Challenges for HCI Researchers. Interactions 23, 5 (aug 2016), 24–25. DOI:http://dx.doi.org/10.1145/2977645 
  40. Digging into User Control: Perceptions of Adherence and Instability in Transparent Models. In Proceedings of the 25th International Conference on Intelligent User Interfaces (IUI ’20). Association for Computing Machinery, New York, NY, USA, 519–530. DOI:http://dx.doi.org/10.1145/3377325.3377491 
  41. Illusions of control, underestimations, and accuracy: a control heuristic explanation. Psychological bulletin 123, 2 (1998), 143.
  42. Player agency and the relevance of decisions. In Joint International Conference on Interactive Digital Storytelling. Springer, 210–215.
  43. The Illusion of Control: Placebo Effects of Control Settings. In Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems (CHI ’18). Association for Computing Machinery, New York, NY, USA, 1–13. DOI:http://dx.doi.org/10.1145/3173574.3173590 
  44. Fairness and Accountability Design Needs for Algorithmic Support in High-Stakes Public Sector Decision-Making. In Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems (CHI ’18). ACM, New York, NY, USA, Article 440, 14 pages. DOI:http://dx.doi.org/10.1145/3173574.3174014 
  45. Designing theory-driven user-centric explainable AI. In Proceedings of the 2019 CHI conference on human factors in computing systems. 1–15.
  46. Daniel M Wegner and Thalia Wheatley. 1999. Apparent mental causation: Sources of the experience of will. American psychologist 54, 7 (1999), 480.
  47. A Qualitative Exploration of Perceptions of Algorithmic Fairness. In Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems (CHI ’18). Association for Computing Machinery, New York, NY, USA, 1–14. DOI:http://dx.doi.org/10.1145/3173574.3174230 
  48. Peta Wyeth. 2007. Agency, tangible technology and young children. In Proceedings of the 6th international conference on Interaction design and children. 101–104.
  49. Matthew D Zeiler and Rob Fergus. 2014. Visualizing and understanding convolutional networks. In European conference on computer vision. Springer, 818–833.
  50. Wencan Zhang and Brian Y Lim. 2022. Towards relatable explainable AI with the perceptual process. In Proceedings of the 2022 CHI Conference on Human Factors in Computing Systems. 1–24.

Summary

No one has generated a summary of this paper yet.

Sign Up to Summarize

Paper to Video (Beta)

No one has generated a video about this paper yet.

Sign Up to Generate All Videos Subscribe on YouTube

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Generate Now

Collections

Sign up for free to add this paper to one or more collections.

Sign Up