When Do LLM Personas Support Visualization Design? A Cross-Model Study of Color Assignment and Chart Choice

2026-07-02

AI Summary

This study investigates whether personified outputs generated by large language models (LLMs) genuinely reflect the influence of user personality on visualization design or are instead confounded by model choice and task formulation. Through systematic evaluation across multiple GPT variants, the authors assess how 43 Big Five personality configurations affect color assignment and chart selection, employing prompt engineering, ANOVA, and cluster-based aggregation, while introducing a no-persona baseline and distinguishing between abstract and concrete concepts. The findings reveal that personality–color associations are highly dependent on model configuration and significantly explain hue variation only for abstract concepts; chart selection is predominantly driven by task context rather than personality. This work provides the first systematic validation of the cross-model stability of personality effects in LLMs, establishing a methodological foundation for controllable personalized visualization.

Abstract

Large language model personas are increasingly used to approximate diverse users during early-stage visualization design, but it remains unclear whether persona-conditioned outputs reflect stable personality effects or artifacts of model choice and task framing. We examine this question across two visualization-relevant tasks: color assignment for abstract and concrete concepts, and chart-idiom preference ratings across task contexts. Using 43 Big Five profiles across GPT-4o-mini, GPT-4.1-mini, and GPT-5-mini, we find that personality-color coupling is highly model-configuration dependent: absent in GPT-4o-mini for all six concepts, consistent in GPT-4.1-mini across all six, and partial in GPT-5-mini for two of six. Concept type further shapes the signal: for abstract concepts, personality explains more hue variance than model identity, while concrete concepts show smaller and comparable effects. In chart choice, trait-aligned cluster aggregation produces stable top-idiom rankings across all nine cluster-context combinations, but a no-persona baseline recovers the same top choice in 8 of 9 model-context cells, indicating that task context drives rank-1 selection more than personality. These findings position LLM personas as exploratory probes for visualization design, not substitutes for human participants, and motivate multi-model testing, concept-type disaggregation, and no-persona baselines in future studies.

Problem

• LLM personas
• visualization design
• personality effects
• color assignment
• chart choice

Innovation

• LLM personas
• visualization design
• cross-model evaluation
• color assignment
• chart choice