Abstract
Personalizing large language models (LLMs) is essential for delivering tailored interactions that improve user experience. Many exist004 ing personalization methods require fine-tuning LLMs for each user, rendering them pro006 hibitively expensive for widespread adoption. Although retrieval-based approaches offer a more compute-efficient alternative, they still de009 pend on large, high-quality datasets that are not consistently available for all users. To address this challenge, we propose CHAMELEON, a scalable and efficient personalization approach that uses (1) self-generated personal prefer014 ence data and (2) representation editing to enable quick and cost-effective personaliza016 tion. Our experiments on various tasks, in017 cluding those from the LaMP personalization benchmark, show that CHAMELEON efficiently adapts models to personal preferences, improv020 ing instruction-tuned models and outperforms two personalization baselines by an average of 40% across two model architectures.
