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

要旨

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.

著者
Paula Akemi. Aoyagui
University of Toronto, Toronto, Ontario, Canada
Kelsey Stemmler
University of Toronto, Toronto, Ontario, Canada
Sharon A. Ferguson
University of Toronto, Toronto, Ontario, Canada
Young-Ho Kim
NAVER AI Lab, Seongnam, Gyeonggi, Korea, Republic of
Anastasia Kuzminykh
University of Toronto, Toronto, Ontario, Canada
DOI

10.1145/3706598.3713248

論文URL

https://dl.acm.org/doi/10.1145/3706598.3713248

動画

会議: CHI 2025

The ACM CHI Conference on Human Factors in Computing Systems (https://chi2025.acm.org/)

セッション: Human-AI Collaboration

G304
7 件の発表
2025-05-01 01:20:00
2025-05-01 02:50:00
日本語まとめ
読み込み中…