FaST: Feature-aware Sampling and Tuning for Personalized Preference Alignment with Limited Data
Preprint
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.Keywords
All Related Versions
This publication has 11 references indexed in Scilit:
- Drift: Decoding-time Personalized Alignments with Implicit User Preferences2025
- A Survey on Personalized Alignment—The Missing Piece for Large Language Models in Real-World Applications2025
- LLM Comparative Assessment: Zero-shot NLG Evaluation through Pairwise Comparisons using Large Language Models2024
- Arithmetic Control of LLMs for Diverse User Preferences: Directional Preference Alignment with Multi-Objective Rewards2024
- G-Eval: NLG Evaluation using Gpt-4 with Better Human Alignment2023
- Character-LLM: A Trainable Agent for Role-Playing2023
- Training Language Models to Follow Instructions with Human Feedback2022
- Dungeons and Dragons as a Dialog Challenge for Artificial Intelligence2022
- Fundamentals of statistical exponential families with applications in statistical decision theory1986
- Rank Analysis of Incomplete Block Designs: I. The Method of Paired ComparisonsBiometrika, 1952