# Audit: Baidu, Google AI overviews barely overlap on sources

Published: 2026-09-28T19:18:30.121Z · Source: arXiv AI-search citations (https://arxiv.org/abs/2609.24407v1)
Source date: 2026-09-21
Flags: research study — academic, WAC@EMNLP 2026; catch-up (Sep 21)
Entities: ai-overviews, google

A cross-lingual audit compared AI-generated overviews on Baidu and Google using English queries from the MS MARCO benchmark and their Chinese translations, in a paper accepted at WAC@EMNLP 2026. Overview availability and which host domains appeared varied substantially by platform and language, with little overlap between the sets of domains visible in each setting's overviews — even as answers matched to the same query intent scored a median cosine similarity of 0.701 to 0.813 across settings. The authors say source-exposure concentration and answer-level similarity capture distinct dimensions of AI-search behavior, so judging an AI overview on its answer text alone misses how differently platforms select and expose sources.

Why it matters: It shows that answer content and source exposure are separate things to track when optimizing across engines and languages — matching a competitor's answer text says nothing about matching its cited sources.

## What this answers

**Do Baidu and Google AI overviews cite the same sources for similar queries?**

No — a cross-lingual audit found little overlap in the domains visible in each platform's AI overviews, even when the generated answers for matched query intents were semantically similar.


Canonical: https://anythingengineoptimization.com/item/2026-09-28-audit-baidu-google-ai-overviews-barely-overlap-on-sources/
From Anything Engine Optimization (AEO Wire) — https://anythingengineoptimization.com/ · Standards: https://anythingengineoptimization.com/standards/