Newest papers

How Language Models Learn Taste: Brand Preference in LLMs

Tapan S. Parikh · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.28272 · cited by 0 works (OpenAlex) · open-access PDF

Spanish

Preguntado para nombrar una marca de zapatos en marcha, los modelos de idioma dicen Nike. Preguntado para recomendar una, dicen Brooks. Este artículo pregunta dónde los modelos aprenden ese gusto. A través de 102 modelos y 42 categorías de marcas, la marca elige un modelo cuando recomienda difiere de la marca que nombra en 26. El campo se mueve junto a una recomendación compartida. Las marcas nominadas son líderes del mercado, y las marcas seleccionadas son principalmente nichos y especialistas. Tres tuberías de formación abiertas muestran dónde esta forma. La formación previa ya contiene la marca recomendada al asesoramiento. El ajuste finamente supervisado enseña al modelo a responder y en su mayoría deja la opción sin cambios. La optimización de preferencias (DPO) enseña al modelo cuál es la respuesta mejor

Machine translation (Meta M2M100); the English original follows.

Abstract

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 brand a model picks when recommending differs from the brand it names in 26. The field moves together to a shared recommendation. The Named brands are market leaders, and the Picked brands are mostly niche and specialist. Three open training pipelines show where this forms. Pretraining already attaches the recommended brand to advice. Supervised fine-tuning teaches the model to answer and mostly leaves the pick unchanged. Preference optimization (DPO) teaches the model which answer is better, and the pick moves in all three pipelines, by 11 to 24 points. The preference data contains almost no brands. DPO moves the model's judgments toward a second set of associations even when the preferred brand is not in the preference data, and the effect reaches beyond brands. Asked to choose a sauce, models switch from ketchup to pesto. We do not know exactly how these preferences arise. We suspect they come from the judge models that decide which answers count as better during preference training. For brands, a recommendation depends less on what a model knows about them than on whether they fit this taste.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Preference, Brand preference, Advertising, Set (abstract data type), Suspect, Field (mathematics)

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange