The Value-Sensitive Conversational Agent Co-Design Framework

TL;DR

The paper addresses the challenge of embedding stakeholder values in conversational agents by introducing the Value-Sensitive Conversational Agent Co-Design Framework (VSCA). It operationalises value-sensitive design through three boundary-object artifacts produced via three design activities, supported by a practitioner toolkit. An evaluation protocol combines a design-workshop case study, semi-structured interviews, and a target-user survey to assess value elicitation, technical utility, and value embodiment in prototypes. The VSCA aims to produce value-embodied CA prototypes and offers a practical, scalable path to integrate ethics into CA development within real-world workflows.

Abstract

Conversational agents (CAs) are gaining traction in both industry and academia, especially with the advent of generative AI and large language models. As these agents are used more broadly by members of the general public and take on a number of critical use cases and social roles, it becomes important to consider the values embedded in these systems. This consideration includes answering questions such as 'whose values get embedded in these agents?' and 'how do those values manifest in the agents being designed?' Accordingly, the aim of this paper is to present the Value-Sensitive Conversational Agent (VSCA) Framework for enabling the collaborative design (co-design) of value-sensitive CAs with relevant stakeholders. Firstly, requirements for co-designing value-sensitive CAs which were identified in previous works are summarised here. Secondly, the practical framework is presented and discussed, including its operationalisation into a design toolkit. The framework facilitates the co-design of three artefacts that elicit stakeholder values and have a technical utility to CA teams to guide CA implementation, enabling the creation of value-embodied CA prototypes. Finally, an evaluation protocol for the framework is proposed where the effects of the framework and toolkit are explored in a design workshop setting to evaluate both the process followed and the outcomes produced.

Figures (8)

• Figure 1: The VSCA Toolkit which operationalises the VSCA Framework. It consists of a guidebook, a set of canvases, information sheets, and blank decks of cards.
• Figure 2: A diagram of the three project phases which covered the three objectives mentioned earlier highlighting the scope of this paper.
• Figure 3: A spectrum depicting guidelines and recommendations as one extreme and design activities and tools as the other extreme, with design processes and frameworks as an imperfect middle ground.
• Figure 4: A model of the requirements needed to reach value embodiment which is framed as a collaborative effort between CA teams and external stakeholders. The values of external stakeholders need to be elicited, and collaboration outcomes need to have a technical utility in order for the CA team to contribute towards value embodiment.
• Figure 5: A diagram showing the activities and boundary objects included in the VSCA framework. These activities and objects are mapped to VSD friedman2006, proposed steps for embedding values in technology flanagan2008, and a conceptual framework for applying VSD to AI systems umbrello2018.