Anything Engine Optimization The rolling record of the AI-search industry.
Dark room with an open window showcasing a blue sea horizon.
Photo by TIME ENERGY on Pexels
single-source — confirmation pending
HackerNoon · Oct 22 ResearchAEOGEO

Study: AI search citations shift depending on query language

What this answers

Does asking an AI search engine the same question in a different language change which sources it cites?
Yes — testing ChatGPT Search, Gemini, Perplexity and Copilot on 40 equivalent questions about Lebanon, a HackerNoon study found Lebanese sources made up 56.7% of Arabic-language citations versus 31.6% of English-language citations for the same questions.
Which AI search engine showed the biggest citation gap between languages?
Gemini had the largest language gap at 34.8 percentage points between Arabic and English citations, ahead of Perplexity (26.8), Copilot (20.4) and ChatGPT Search (18.5), per the same study.

Computational researcher Mohamed Soufan asked ChatGPT Search, Gemini, Perplexity and Copilot 40 equivalent questions about Lebanon — across topics like economy, banking and health — in both English and Arabic, collecting 320 responses, per his own HackerNoon write-up. Lebanese sources made up 56.7% of citations in Arabic-language answers versus 31.6% in English for the same questions, a 25.1-point gap; Gemini showed the widest split between the two languages (34.8 points), ahead of Perplexity (26.8), Copilot (20.4) and ChatGPT Search (18.5). International organizations accounted for 21% of English citations but only 12% of Arabic ones, while news and media sources were 24% of Arabic citations versus 10% of English. Soufan notes the test captured each system at a single point in time with one response per combination, and did not assess whether the language-based differences affected factual accuracy.

Why it matters: AI-visibility testing done only in English can miss how a brand or topic is actually represented to non-English speakers — a gap this quantifies for source citations the way an October 13 study quantified it for brand recommendations.

The record: ChatGPTGeminiPerplexity

Via HackerNoon ↗

Posted to the wire October 22, 2026. Edited by Joe Balewski.