SME-in-the-loop: Interaction Preferences when Supervising Bots in Human-AI Communities

Abstract

Subject matter experts play an important role in customer support communities by responding to user queries. Some communities have adopted chatbots in addition to SMEs to address commonly asked questions. Yet, SME-bot interactions, particularly teaching paradigms between SMEs and bots remain understudied. We investigate human-AI machine teaching interactions in a scenario-based study (n=48). Participants selected their preferred teaching method in simulated community interactions with a consumer, an SME, and an AI Bot. We investigated preferences across three interactions: demonstration (Showing), preference elicitation (Sorting), and labeling (Categorization). Participants preferred the Showing interaction, followed by Sorting and Categorizing. Participants changed their preferences from lower-efort interactions when considering downstream outcomes. Users considered the community’s perception of interactions between the bot and the SME, specifcally transparency of learning outcome, orientation of the feedback, querying the bot and disruptiveness of the interaction. We discuss implications for our fndings for teaching interactions in human-AI communities.