{"ID":2885940,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.04698","arxiv_id":"2508.04698","title":"FaST: Feature-aware Sampling and Tuning for Personalized Preference Alignment with Limited Data","abstract":"LLM-powered conversational assistants are often deployed in a one-size-fits-all manner, which fails to accommodate individual user preferences. Recently, LLM personalization -- tailoring models to align with specific user preferences -- has gained increasing attention as a way to bridge this gap. In this work, we specifically focus on a practical yet challenging setting where only a small set of preference annotations can be collected per user -- a problem we define as Personalized Preference Alignment with Limited Data (PPALLI). To support research in this area, we introduce two datasets -- DnD and ELIP -- and benchmark a variety of alignment techniques on them. We further propose FaST, a highly parameter-efficient approach that leverages high-level features automatically discovered from the data, achieving the best overall performance.","short_abstract":"LLM-powered conversational assistants are often deployed in a one-size-fits-all manner, which fails to accommodate individual user preferences. Recently, LLM personalization -- tailoring models to align with specific user preferences -- has gained increasing attention as a way to bridge this gap. In this work, we speci...","url_abs":"https://arxiv.org/abs/2508.04698","url_pdf":"https://arxiv.org/pdf/2508.04698v1","authors":"[\"Thibaut Thonet\",\"Germán Kruszewski\",\"Jos Rozen\",\"Pierre Erbacher\",\"Marc Dymetman\"]","published":"2025-08-06T17:58:26Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Large Language Model\"]","has_code":false}