arXiv:2606.25787 · v2
Cited Web Sources in LLM Answers about Brands: A Multilingual Audit
摘要
Displayed citations make part of generative search observable, but they do not reveal its complete retrieval process. This audit covers three archived datasets containing 167,551 URL-bearing citation entries across 128 brands, 13 languages and 12 home markets. In the principal Nordic-Baltic component, 3,863 of 21,033 registrable domains account for 80% of 131,514 citations. Wikipedia leads in 11 of 12 query languages. A recovered, separate brand-associated website classification retains 131,512 entries: 108,410 (82.4%) fall outside its brand-associated category and 23,102 (17.6%) inside. This classification does not establish legal ownership. In the full 57-brand Polish aggregate, four recruitment hosts receive 637 citations against 297 for Polish Wikipedia. The results show why normalization, classification rules and denominators belong in citation audits. They describe displayed links without estimating causal effects on brand reputation.
作者备注:13 pages, 7 tables. Corrected domain counts and Polish cohort scope; replaced the unreproduced 85.7% ownership claim with a separately reproduced 82.4% brand-associated website classification. Ancillary reproduction code and updated related work included