# Silver-Tongued and Sundry: Exploring Intersectional Pronouns with ChatGPT

arXiv: https://arxiv.org/abs/2405.08238 · HTML: https://mlsanity.com/paper/2405.08238/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 74 references that are in the map.
- First posted on arXiv 13 May 2024.

## Builds on (most cited first, 8 of 8)

- [Mitigating Gender Bias in Natural Language Processing: Literature Review](https://mlsanity.com/paper/1906.08976/) (2019)
- [On Measuring Gender Bias in Translation of Gender-neutral Pronouns](https://mlsanity.com/paper/1905.11684/) (2019)
- [What Pronouns for Pepper? A Critical Review of Gender/ing in Research](https://mlsanity.com/paper/2212.04206/) (2022)
- [Exploring Gender-Expansive Categorization Options for Robots](https://mlsanity.com/paper/2205.00191/) (2022)
- [Transcending the "Male Code": Implicit Masculine Biases in NLP Contexts](https://mlsanity.com/paper/2304.12810/) (2023)
- [Can Voice Assistants Sound Cute? Towards a Model of Kawaii Vocalics](https://mlsanity.com/paper/2304.12809/) (2023)
- ["I'm" Lost in Translation: Pronoun Missteps in Crowdsourced Data Sets](https://mlsanity.com/paper/2304.13557/) (2023)
- [Towards Social Identity in Socio-Cognitive Agents](https://mlsanity.com/paper/2001.07142/) (2020)

## Built on by (most cited first, 6 of 6)

- [Understanding the LLM-ification of CHI: Unpacking the Impact of LLMs at CHI through a Systematic Literature Review](https://mlsanity.com/paper/2501.12557/) (2025)
- [Social Identity in Human-Agent Interaction: A Primer](https://mlsanity.com/paper/2508.16609/) (2025)
- [ChatGPT and U(X): A Rapid Review on Measuring the User Experience](https://mlsanity.com/paper/2503.15808/) (2025)
- [More-than-Human Storytelling: Designing Longitudinal Narrative Engagements with Generative AI](https://mlsanity.com/paper/2505.23780/) (2025)
- [Inter(sectional) Alia(s): Ambiguity in Voice Agent Identity via Intersectional Japanese Self-Referents](https://mlsanity.com/paper/2506.01998/) (2025)
- [Operationalizing Perceptions of Agent Gender: Foundations and Guidelines](https://mlsanity.com/paper/2603.26682/) (2026)

## Abstract (arXiv)

ChatGPT is a conversational agent built on a large language model. Trained on a significant portion of human output, ChatGPT can mimic people to a degree. As such, we need to consider what social identities ChatGPT simulates (or can be designed to simulate). In this study, we explored the case of identity simulation through Japanese first-person pronouns, which are tightly connected to social identities in intersectional ways, i.e., intersectional pronouns. We conducted a controlled online experiment where people from two regions in Japan (Kanto and Kinki) witnessed interactions with ChatGPT using ten sets of first-person pronouns. We discovered that pronouns alone can evoke perceptions of social identities in ChatGPT at the intersections of gender, age, region, and formality, with caveats. This work highlights the importance of pronoun use for social identity simulation, provides a language-based methodology for culturally-sensitive persona development, and advances the potential of intersectional identities in intelligent agents.