# Study: GEO rewriting can shift AI election-answer exposure

Published: 2026-10-16T01:48:42.412Z · Source: arXiv GEO (https://arxiv.org/abs/2610.21330v1)
Source date: 2026-10-15
Flags: research study

A new benchmark, VoteGEO-Bench, tests how generative engine optimization (GEO) rewriting changes which webpages AI engines cite on election queries covering the 2024 U.S. presidential race and Japan's 2026 House of Representatives election, per researchers Shiqi Zhang and Xiaokui Xiao. Rewriting without naming a target rarely increased that page's exposure, while rewriting that named a target and reorganized or strengthened its argument did; the study also found that an AI engine's baseline exposure gap between explicit partisan voter identities can exceed the gain from rewriting a single page.

Why it matters: It extends the GEO-manipulation risk this wire has tracked into a domain where skewed answer visibility carries direct political stakes, rather than just commercial ones.

## What this answers

**Can content rewriting change which election sources an AI engine cites?**

Yes — per a new VoteGEO-Bench study, rewriting that names a target page and strengthens its argument or organization increased that page's exposure in AI election answers, while rewriting without naming a target rarely did.

**Does a voter's partisan identity affect what an AI engine shows about elections?**

Per the study, giving an AI engine an explicit partisan voter persona can create a baseline exposure gap bigger than the gain from rewriting one webpage.


Canonical: https://anythingengineoptimization.com/item/2026-10-16-study-geo-rewriting-can-shift-ai-election-answer-exposure/
From Anything Engine Optimization (AEO Wire) — https://anythingengineoptimization.com/ · Standards: https://anythingengineoptimization.com/standards/