A Day in Their Shoes: Using LLM-Based Perspective-Taking Interactive Fiction to Reduce Stigma Toward Dirty Work

TL;DR

The paper tackles public stigma toward 'dirty work' by proposing an LLM-based Interactive Fiction (IF) framework that enables perspective-taking through immersive, first-person simulations of four occupations. Using GPT-4o, the study exposes 100 Chinese participants to dynamic, adaptive scenarios and measures shifts in empathy, knowledge, and perceived closeness to workers, complemented by 15 qualitative interviews. Quantitatively, participants showed increased understanding and empathy with no significant differences across occupations; qualitatively, mechanisms such as cognitive reframing, direct exposure to pressures, and emotional resonance were identified, alongside benefits and challenges of the approach. The findings suggest that AI-driven, interactive narratives can be a scalable tool for stigma reduction and social equity in marginalized professions, while underscoring the need for multimodal enhancements and longitudinal validation to maximize impact and mitigate potential stereotype reinforcement.

Abstract

Occupations referred to as "dirty work" often face entrenched social stigma, which adversely affects the mental health of workers in these fields and impedes occupational equity. In this study, we propose a novel Interactive Fiction (IF) framework powered by Large Language Models (LLMs) to encourage perspective-taking and reduce biases against these stigmatized yet essential roles. Through an experiment with participants (n = 100) across four such occupations, we observed a significant increase in participants' understanding of these occupations, as well as a high level of empathy and a strong sense of connection to individuals in these roles. Additionally, qualitative interviews with participants (n = 15) revealed that the LLM-based perspective-taking IF enhanced immersion, deepened emotional resonance and empathy toward "dirty work," and allowed participants to experience a sense of professional fulfillment in these occupations. However, participants also highlighted ongoing challenges, such as limited contextual details generated by the LLM and the unintentional reinforcement of existing stereotypes. Overall, our findings underscore that an LLM-based perspective-taking IF framework offers a promising and scalable strategy for mitigating stigma and promoting social equity in marginalized professions.