aiqbench analysis
This research identifies "Prompt Privilege," where semantically identical requests yield different results based on user prompting expertise, and introduces the Prompt Equity Transformer (PET) to normalize inputs for fairer model interactions. By shifting optimization from users to the system, the proposed solution directly addresses accessibility barriers in critical domains like healthcare and education without relying on adversarial attack frameworks.
Prompt Privilege in Large Language Models: Measuring and Mitigating Barriers to Equitable AI Access
From arXiv
Full textarXiv:2608.08942v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used in healthcare, education, public services, and everyday decision making. They should provide comparable assistance regardless of users' literacy, communication style, or prompt-engineering expertise. However, research on prompt robustness primarily focuses on adversarial attacks, prompt injection, and prompt optimization, overlooking whether semantically equivalent requests receive different responses simply because they are phrased differently. We call this accessibility challenge "Prompt Privilege": users with greater prompting expertise obtain better model performance despite expressing the same underlying intent.
To address this problem, we propose the Prompt Equity Score (PES), a metric for evaluating performance consistency across user populations, and the Prompt Equity Transformer (PET), an LLM-based agent that automatically transforms user requests into semantically equivalent prompts while preserving their intent. PET shifts prompt optimization from users to AI systems, serving as an accessibility layer between users and foundation models. Experiments on MedQA reveal measurable prompt privilege, with statistically significant performance disparities between low-literacy and expert-prompting cohorts.
Applying PET reduces these differences, with no pairwise cohort differences reaching statistical significance in our evaluation. These results suggest that accessibility-oriented prompt normalization can improve equitable AI access. By introducing prompt privilege as a new dimension of AI accessibility and PET as a practical solution, this work advances system-centered accessibility and provides a foundation for fairer, more trustworthy, and more inclusive AI systems.
Abstract:Large language models (LLMs) are increasingly used in healthcare, education, public services, and everyday decision making. They should provide comparable assistance regardless of users' literacy, communication style, or prompt-engineering expertise. However, research on prompt robustness primarily focuses on adversarial attacks, prompt injection, and prompt optimization, overlooking whether semantically equivalent requests receive different responses simply because they are phrased differently. We call this accessibility challenge "Prompt Privilege": users with greater prompting expertise obtain better model performance despite expressing the same underlying intent.
To address this problem, we propose the Prompt Equity Score (PES), a metric for evaluating performance consistency across user populations, and the Prompt Equity Transformer (PET), an LLM-based agent that automatically transforms user requests into semantically equivalent prompts while preserving their intent. PET shifts prompt optimization from users to AI systems, serving as an accessibility layer between users and foundation models. Experiments on MedQA reveal measurable prompt privilege, with statistically significant performance disparities between low-literacy and expert-prompting cohorts.
Applying PET reduces these differences, with no pairwise cohort differences reaching statistical significance in our evaluation. These results suggest that accessibility-oriented prompt normalization can improve equitable AI access. By introducing prompt privilege as a new dimension of AI accessibility and PET as a practical solution, this work advances system-centered accessibility and provides a foundation for fairer, more trustworthy, and more inclusive AI systems.
Computation and Language (cs.CL)
arXiv:2608.08942 [cs.CL]
(or arXiv:2608.08942v2 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2608.08942 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 315 words
Related coverage
SpatialOPSD: Self-Distilling Spatial Intelligence from Verified Coding Agent Traces
arXiv · Oct 9, 2026

Top 10 Best Just-in-Time (JIT) Access Tools in 2026 [Ranked & Scored]
Cybersecurity News · Oct 6, 2026
MiniScope: Authorizing Agents with Least-Privilege Permissions
arXiv · Oct 7, 2026

Top 10 Best Container Security Tools in 2026
Cybersecurity News · Sep 15, 2026