Same Question, Different Answer? Measuring and Mitigating Prompt Privilege for Equitable AI Access

Abstract

Large language models (LLMs) are increasingly integrated into healthcare, education, public services, and everyday decision making. They should provide comparable assistance regardless of a user's literacy, communication style, or prompt-engineering expertise. However, existing research on prompt robustness primarily focuses on adversarial attacks, prompt injection, and prompt optimization, while overlooking whether semantically equivalent requests receive different responses simply because they

Categories

Framework mappings

Suggested from the entry's categories.

@misc{jin2026same,
  title = {{Same Question, Different Answer? Measuring and Mitigating Prompt Privilege for Equitable AI Access}},
  author = {Li Jin and Lang-Xiang Hu and Bin-Qi Shen and Han-Yu Cai and Yu-Ting Xin},
  year = {2026},
  month = aug,
  eprint = {2608.08942},
  archivePrefix = {arXiv},
  url = {https://www.semanticscholar.org/paper/fe4a2c7e3cb87a251832379d2d8903fdaa601d2a}
}