A Matter of Perspective(s): Contrasting Human and LLM Argumentation in Subjective Decision-Making on Subtle Sexism

Abstract

In subjective decision-making, where decisions are based on contextual interpretation, Large Language Models (LLMs) can be integrated to present users with additional rationales to consider. The diversity of these rationales is mediated by the ability to consider the perspectives of different social actors. However, it remains unclear whether and how models differ in the distribution of perspectives they provide. We compare the perspectives taken by humans and different LLMs when assessing subtle sexism scenarios. We show that these perspectives can be classified within a finite set (perpetrator, victim, decision-maker), consistently present in argumentations produced by humans and LLMs, but in different distributions and combinations, demonstrating differences and similarities with human responses, and between models. We argue for the need to systematically evaluate LLMs' perspective-taking to identify the most suitable models for a given decision-making task. We discuss the implications for model evaluation.

Accepted at CHI Conference on Human Factors in Computing Systems (CHI '25), April 26-May 1, 2025, Yokohama, Japan

References in corpus (7)

• Effect of Confidence and Explanation on Accuracy and Trust Calibration in AI-Assisted Decision Making
• 'It's Reducing a Human Being to a Percentage'; Perceptions of Justice in Algorithmic Decisions
• Gender bias and stereotypes in Large Language Models
• BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation
• Jury Learning: Integrating Dissenting Voices into Machine Learning Models
• "I'm fully who I am": Towards Centering Transgender and Non-Binary Voices to Measure Biases in Open Language Generation
• Capturing Humans' Mental Models of AI: An Item Response Theory Approach