PersonalLLM: Tailoring LLMs to Individual Preferences
This work addresses the need for personalized AI interactions by providing a benchmark for developing algorithms that handle data sparsity, though it is incremental as it builds on existing alignment methods.
The authors tackled the problem of personalizing LLMs to individual user preferences by creating a public benchmark called PersonalLLM, which includes open-ended prompts with diverse answers to simulate heterogeneous preferences, and they demonstrated its utility with basic in-context learning and meta-learning baselines.
As LLMs become capable of complex tasks, there is growing potential for personalized interactions tailored to the subtle and idiosyncratic preferences of the user. We present a public benchmark, PersonalLLM, focusing on adapting LLMs to provide maximal benefits for a particular user. Departing from existing alignment benchmarks that implicitly assume uniform preferences, we curate open-ended prompts paired with many high-quality answers over which users would be expected to display heterogeneous latent preferences. Instead of persona-prompting LLMs based on high-level attributes (e.g., user's race or response length), which yields homogeneous preferences relative to humans, we develop a method that can simulate a large user base with diverse preferences from a set of pre-trained reward models. Our dataset and generated personalities offer an innovative testbed for developing personalization algorithms that grapple with continual data sparsity--few relevant feedback from the particular user--by leveraging historical data from other (similar) users. We explore basic in-context learning and meta-learning baselines to illustrate the utility of PersonalLLM and highlight the need for future methodological development. Our dataset is available at https://huggingface.co/datasets/namkoong-lab/PersonalLLM