For socially sensitive tasks like hate speech detection, the quality of explanations from Large Language Models (LLMs) is crucial for factors like user trust and model alignment. While Persona prompting (PP) is increasingly used as a way to steer model towards user-specific generation, its effect on model rationales remains underexplored. We investigate how LLM-generated rationales vary when conditioned on different simulated demographic personas. Using datasets annotated with word-level rationales, we measure agreement with human annotations from different demographic groups, and assess the impact of PP on model bias and human alignment. Our evaluation across three LLMs results reveals three key findings: (1) PP improving classification on the most subjective task (hate speech) but degrading rationale quality. (2) Simulated personas fail to align with their real-world demographic counterparts, and high inter-persona agreement shows models are resistant to significant steering. (3) Models exhibit consistent demographic biases and a strong tendency to over-flag content as harmful, regardless of PP. Our findings reveal a critical trade-off: while PP can improve classification in socially-sensitive tasks, it often comes at the cost of rationale quality and fails to mitigate underlying biases, urging caution in its application.
Persona Prompting as a Lens on LLM Social Reasoning
Persona prompting affects large language model rationales in socially sensitive tasks by improving classification accuracy but reducing explanation quality while failing to eliminate demographic biases.
- Year
- 2026
- Venue
- arXiv 2026
- Authors
- 6
- Hosting
- Abstract onlyARXIV-DEFAULT
Cite
Notes
Only stored in your browser.
Attribution
- Abstract & full text
- arxiv.org/abs/2601.20757ARXIV-DEFAULT
- TL;DR
- Semantic Scholar