Personalize Your LLM: Fake it then Align it
This addresses the problem of costly personalization for LLMs, offering a scalable solution for improving user experience, though it appears incremental as it builds on existing personalization methods.
The paper tackles the challenge of personalizing large language models (LLMs) efficiently by proposing CHAMELEON, which uses self-generated personal preference data and representation editing, resulting in a 40% average improvement over baselines on personalization tasks.
Personalizing large language models (LLMs) is essential for delivering tailored interactions that improve user experience. Many existing personalization methods require fine-tuning LLMs for each user, rendering them prohibitively expensive for widespread adoption. Although retrieval-based approaches offer a more compute-efficient alternative, they still depend 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 preference data and (2) representation editing to enable quick and cost-effective personalization. Our experiments on various tasks, including those from the LaMP personalization benchmark, show that CHAMELEON efficiently adapts models to personal preferences, improving instruction-tuned models and outperforms two personalization baselines by an average of 40% across two model architectures.