Principled Personas: Defining and Measuring the Intended Effects of Persona Prompting on Task Performance
This work addresses the inconsistent and poorly understood impacts of persona prompting for users of language models, highlighting incremental insights into when and why personas improve task performance.
The study analyzed the effectiveness of expert persona prompting in language models across 27 tasks, finding that expert personas often lead to positive or non-significant performance changes, but models are highly sensitive to irrelevant persona details, with performance drops of almost 30 percentage points.
Expert persona prompting -- assigning roles such as expert in math to language models -- is widely used for task improvement. However, prior work shows mixed results on its effectiveness, and does not consider when and why personas should improve performance. We analyze the literature on persona prompting for task improvement and distill three desiderata: 1) performance advantage of expert personas, 2) robustness to irrelevant persona attributes, and 3) fidelity to persona attributes. We then evaluate 9 state-of-the-art LLMs across 27 tasks with respect to these desiderata. We find that expert personas usually lead to positive or non-significant performance changes. Surprisingly, models are highly sensitive to irrelevant persona details, with performance drops of almost 30 percentage points. In terms of fidelity, we find that while higher education, specialization, and domain-relatedness can boost performance, their effects are often inconsistent or negligible across tasks. We propose mitigation strategies to improve robustness -- but find they only work for the largest, most capable models. Our findings underscore the need for more careful persona design and for evaluation schemes that reflect the intended effects of persona usage.