Personality Shapes Gender Bias in Persona-Conditioned LLM Narratives Across English and Hindi: An Empirical Investigation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918468365844480 |
|---|---|
| author | Kumar, Tanay Gautam, Shreya Chadha, Aman Jain, Vinija Pierri, Francesco |
| author_facet | Kumar, Tanay Gautam, Shreya Chadha, Aman Jain, Vinija Pierri, Francesco |
| contents | Large Language Models (LLMs) are increasingly deployed in persona-driven applications such as education, customer service, and social platforms, where models are prompted to adopt specific personas when interacting with users. While persona conditioning can improve user experience and engagement, it also raises concerns about how personality cues may interact with gender biases and stereotypes. In this work, we present a controlled study of persona-conditioned story generation in English and Hindi, where each story portrays a working professional in India producing context-specific artifacts (e.g., lesson plans, reports, letters) under systematically varied persona gender, occupational role, and personality traits from the HEXACO and Dark Triad frameworks. Across 23,400 generated stories from six state-of-the-art LLMs, we find that personality traits are significantly associated with both the magnitude and direction of gender bias. In particular, Dark Triad personality traits are consistently associated with higher gender-stereotypical representations compared to socially desirable HEXACO traits, though these associations vary across models and languages. Our findings demonstrate that gender bias in LLMs is not static but context-dependent. This suggests that persona-conditioned systems used in real-world applications may introduce uneven representational harms, reinforcing gender stereotypes in generated educational, professional, or social content. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_23600 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Personality Shapes Gender Bias in Persona-Conditioned LLM Narratives Across English and Hindi: An Empirical Investigation Kumar, Tanay Gautam, Shreya Chadha, Aman Jain, Vinija Pierri, Francesco Computation and Language Large Language Models (LLMs) are increasingly deployed in persona-driven applications such as education, customer service, and social platforms, where models are prompted to adopt specific personas when interacting with users. While persona conditioning can improve user experience and engagement, it also raises concerns about how personality cues may interact with gender biases and stereotypes. In this work, we present a controlled study of persona-conditioned story generation in English and Hindi, where each story portrays a working professional in India producing context-specific artifacts (e.g., lesson plans, reports, letters) under systematically varied persona gender, occupational role, and personality traits from the HEXACO and Dark Triad frameworks. Across 23,400 generated stories from six state-of-the-art LLMs, we find that personality traits are significantly associated with both the magnitude and direction of gender bias. In particular, Dark Triad personality traits are consistently associated with higher gender-stereotypical representations compared to socially desirable HEXACO traits, though these associations vary across models and languages. Our findings demonstrate that gender bias in LLMs is not static but context-dependent. This suggests that persona-conditioned systems used in real-world applications may introduce uneven representational harms, reinforcing gender stereotypes in generated educational, professional, or social content. |
| title | Personality Shapes Gender Bias in Persona-Conditioned LLM Narratives Across English and Hindi: An Empirical Investigation |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2604.23600 |