FaST: Feature-aware Sampling and Tuning for Personalized Preference Alignment with Limited Data
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913977820250112 |
|---|---|
| author | Thonet, Thibaut Kruszewski, Germán Rozen, Jos Erbacher, Pierre Dymetman, Marc |
| author_facet | Thonet, Thibaut Kruszewski, Germán Rozen, Jos Erbacher, Pierre Dymetman, Marc |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_04698 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FaST: Feature-aware Sampling and Tuning for Personalized Preference Alignment with Limited Data Thonet, Thibaut Kruszewski, Germán Rozen, Jos Erbacher, Pierre Dymetman, Marc Computation and Language 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. |
| title | FaST: Feature-aware Sampling and Tuning for Personalized Preference Alignment with Limited Data |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2508.04698 |