Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Guidelines for Integrating Value Sensitive Design in Responsible AI Toolkits

Malak Sadek, Marios Constantinides, Daniele Quercia, Céline Mougenot

TL;DR

These findings show that collaborative and educational design features within RAI toolkits, including illustrative examples and open-ended cues, facilitate an understanding of human and ethical values, and empower researchers to incorporate values into AI systems.

Abstract

Value Sensitive Design (VSD) is a framework for integrating human values throughout the technology design process. In parallel, Responsible AI (RAI) advocates for the development of systems aligning with ethical values, such as fairness and transparency. In this study, we posit that a VSD approach is not only compatible, but also advantageous to the development of RAI toolkits. To empirically assess this hypothesis, we conducted four workshops involving 17 early-career AI researchers. Our aim was to establish links between VSD and RAI values while examining how existing toolkits incorporate VSD principles in their design. Our findings show that collaborative and educational design features within these toolkits, including illustrative examples and open-ended cues, facilitate an understanding of human and ethical values, and empower researchers to incorporate values into AI systems. Drawing on these insights, we formulated six design guidelines for integrating VSD values into the development of RAI toolkits.

Guidelines for Integrating Value Sensitive Design in Responsible AI Toolkits

TL;DR

These findings show that collaborative and educational design features within RAI toolkits, including illustrative examples and open-ended cues, facilitate an understanding of human and ethical values, and empower researchers to incorporate values into AI systems.

Abstract

Value Sensitive Design (VSD) is a framework for integrating human values throughout the technology design process. In parallel, Responsible AI (RAI) advocates for the development of systems aligning with ethical values, such as fairness and transparency. In this study, we posit that a VSD approach is not only compatible, but also advantageous to the development of RAI toolkits. To empirically assess this hypothesis, we conducted four workshops involving 17 early-career AI researchers. Our aim was to establish links between VSD and RAI values while examining how existing toolkits incorporate VSD principles in their design. Our findings show that collaborative and educational design features within these toolkits, including illustrative examples and open-ended cues, facilitate an understanding of human and ethical values, and empower researchers to incorporate values into AI systems. Drawing on these insights, we formulated six design guidelines for integrating VSD values into the development of RAI toolkits.
Paper Structure (28 sections, 8 figures, 3 tables)

This paper contains 28 sections, 8 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Background and Related Work
  3. Value Sensitive Design and Alternative Frameworks
  4. Responsible AI Toolkits
  5. Forms and Mediums
  6. Design Decisions
  7. Methodology
  8. Selecting and presenting RAI toolkits
  9. Mapping VSD values to RAI values
  10. Conducting Workshops
  11. Participants
  12. Workshop Structure and Activities
  13. Data Collection & Analysis
  14. Results
  15. RQ1: How closely do Value Sensitive Design (VSD) values align with Responsible AI (RAI) values integrated into RAI toolkits?
  16. ...and 13 more sections

Figures (8)

  • Figure 1: A list of the values stated by VSD as being "often implicated in system design" friedman2002 and their descriptions in a Miro board.
  • Figure 2: A screenshot of the Nokia AI Design toolkit with descriptions of each element in the interface in blue boxes.
  • Figure 3: Screenshots of the two types of slides in the MIT Blindspots toolkit: the overview slide (top), and an example of a detailed slide (bottom).
  • Figure 4: A flow diagram outlining the workshops' activities and their goals and duration.
  • Figure 5: The Miro board for Activity 1 after participants had assigned values to the Nokia AI Design toolkit and reached a consensus.
  • ...and 3 more figures