Metraipolis › archive › dc_e68c7abe89a9

System Attribution in LLM Brand Recommendations: Single Responses Identify the System, Aggregated Brand Profiles Do Not Transfer — arXiv:2610.00253

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.00253
License (as archived)
CC0-1.0
Archived
2026-10-06T13:56:54.310Z
SHA-256 of the archived text
f721c5d47b6ec011d476020bae01ad472ac3d7751872ce8ed4e4391ce13b0fa0
Stable URL of this page
https://metraipolis.com/documento/dc_e68c7abe89a9

How to cite

System Attribution in LLM Brand Recommendations: Single Responses Identify the System, Aggregated Brand Profiles Do Not Transfer — arXiv:2610.00253 — arXiv (en), https://arxiv.org/abs/2610.00253 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e68c7abe89a9 (Metraipolis archive dc_e68c7abe89a9, sha256 f721c5d47b6ec011d476020bae01ad472ac3d7751872ce8ed4e4391ce13b0fa0)
BibTeX
@misc{dce68c7abe89a9,
  title = {System Attribution in LLM Brand Recommendations: Single Responses Identify the System, Aggregated Brand Profiles Do Not Transfer — arXiv:2610.00253},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.00253},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e68c7abe89a9; sha256 f721c5d47b6ec011d476020bae01ad472ac3d7751872ce8ed4e4391ce13b0fa0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.00253. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Audits of AI visibility summarise the brand recommendations of deployed language models into per-system profiles. We test whether such a profile describes the system on one corpus of 6,475 stored responses (6,324 analysable) collected between December 2025 and February 2026 from five deployed endpoints across gift-recommendation, corporate-reputation and category-ownership queries. The collection harness cut many answers short: 83.1% of Gemini 3 Flash answers in category ownership end mid-sentence under a 1,024-token output cap. With every answer cut to its first 800 characters, a character n-gram classifier cross-validated by prompt attributes one response to GPT-5.2, Gemini 3 Flash, Gemini 3 Flash with search, Grok or Perplexity sonar-pro with 97.84% accuracy (5,028 responses, 383 prompts, majority class 31.5%, 30 split seeds). Length alone falls to the majority rate, 24 formatting statistics reach 95.79%, and masking brand names and capitalised tokens leaves 97.72%. Held-out query conditions keep 97.43% weighted by size and 88.0% unweighted; in a retrieval-grounded arm that changes the harness, no Grok answer is attributed to Grok (0/120). Aggregated into 50 model-by-domain-by-condition units, twelve behavioural features separate four systems at 66.53% under grouped cross-validation, against a label-permutation null with mean 33.71% and 95th percentile 46.0%. Across domains the aggregate profile fails: a forest trained on category-ownership units assigns all 22 gift units to the wrong system, consistent with a reversal in brand volume (8.41 against 0.94 brands per response in gifts, 3.01 against 3.91 in category ownership), while single responses transfer at 89.92% balanced accuracy. The surface form of an answer carries the system across the query domains tested; aggregated brand behaviour does not, and the uncrossed design cannot separate the system from the domain or the harness.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-02 in cs.CL).
Categorie arXiv: Information Retrieval (cs.IR) ; Computation and Language (cs.CL); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.00253 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-06T12:15:34.800Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).