The study examines how repeated identical buying questions affect the brand recommendations of large language models (LLMs) with and without web‑search retrieval. Across 300 question‑engine cells, five engines that did not use web search continued to add new, previously unseen brands up to run 15, while the single retrieval‑enabled engine’s list plateaued earlier. Domain citations continued to grow throughout the runs, indicating that LLMs keep accumulating source diversity even as brand lists stabilize.
By Dmitrij \.Zatuchin
arXiv:2606. 17443v1 Announce Type: new Abstract: Large language models (LLMs) are becoming a major way for consumers to find products, but we do not yet understand how brands compete in this new channel.
By Xi Chu, Yupeng Hou
The study evaluates whether aggregated brand recommendation profiles can identify the language model that generated them. Using 6,475 responses from five deployed endpoints, a character‑n‑gram classifier accurately attributes single responses to the correct system (97.84% accuracy). However, when responses are aggregated into domain‑condition units, the classifier’s performance drops to 66.53%, and a forest model misclassifies all gift‑domain units, indicating that aggregated brand behaviour does not reliably reveal the underlying system.
By Dmitrij \.Zatuchin
arXiv:2609.18729v1 Announce Type: cross
Abstract: Consumers increasingly use AI chatbots for advice on what to buy. With companies like OpenAI and Google monetising their AI through advertising, this...
By Lucas G. Uberti-Bona Marin, Thales Bertaglia, Giovanni Astante, Bram Rijsbosch, Gijs van Dijck, Anik\'o Hann\'ak, Gerasimos Spanakis, Konrad Kollnig
The paper investigates how large language models develop brand preferences, noting that models often name market‑leading brands like Nike when asked for a running shoe brand but recommend niche brands such as Brooks. Across 102 models and 42 brand categories, the brand chosen for recommendation differs from the named brand in 26% of cases, and preference optimization (DPO) shifts these choices by 11–24 points. The study suggests that pretraining already links recommended brands to advice, supervised fine‑tuning preserves these preferences, and DPO can shift them even when the preferred brand is absent from the preference data, indicating that the judge models used in training play a key role.
By Tapan Parikh
arXiv:2608.30023v1 Announce Type: cross
Abstract: Generative engines such as ChatGPT, Gemini, and Perplexity answer buyer questions directly and name a shortlist of brands inside the answer. Studying...
By Dmitrij \.Zatuchin, Daniil Dzemesjuk
arXiv:2606. 26116v1 Announce Type: cross Abstract: A brand whose customers use both ChatGPT and Claude for product recommendations faces a strategic choice: a single optimization playbook, or one per provider?
By Will Jack, Noah Lehman, Keller Maloney, Sarah Xu
Asked to name a running shoe brand, language models say Nike. Asked to recommend one, they say Brooks. This paper asks where models learn that taste. Across 102 models and 42 brand categories, the bra...
arXiv:2609.18341v1 Announce Type: cross
Abstract: When someone asks an AI assistant which doctor to see or which firm to trust with their savings, the answer is a referral. We audit AI provider recom...
By Hazem Ibrahim, Yasir Zaki
arXiv:2606. 09204v1 Announce Type: new Abstract: We present a reproducible failure mode of safety training in RAG-based LLM recommendation -- the Injection Paradox -- in which prompt injections embedded in retrieved documents backfire against the attacker, suppressing the target brand below the injection-free baseline.
By Hyunseok Paeng
The study audits large language model (LLM) outputs by measuring how well repeated queries recover a collected set of responses versus the full set of possible outputs. Using sample-based rarefaction on 4,500 responses from 50 buying questions across six configurations, the authors find historical-dictionary median recovery rates between 92.6% and 95.2%, which drop to 89.5%–94.7% after re‑adjudicating all candidate strings. Additional analyses with Gemini 3.1 Pro annotations and matched roster data confirm that recovery percentages vary with extraction methods, question selection, and the finite reference collection, underscoring the need for explicit measurement definitions and sensitivity analyses in LLM audits.
By Dmitrij \.Zatuchin
The Dice Roll Method is a standardized protocol for auditing large language model brand recommendations through repeated queries. It decomposes total response variance into sampling, prompt‑phrasing, run‑to‑run, and model‑version components, and uses a negative‑binomial mixed model, Cliff’s delta, and bootstrap techniques to guide iteration counts. The study identifies three iteration tiers—exploratory (n=5), confirmatory (n=10), and rigorous (n=15)—and recommends a compact battery of four complementary metrics for robust evaluation.
By Dmitrij \.Zatuchin