Guided Profile Generation Improves Personalization with LLMs
This addresses personalization challenges in commercial systems like recommendation platforms, though it appears incremental as it builds on existing context enrichment approaches.
The paper tackles the problem of LLMs struggling to effectively use sparse personal context for personalization by proposing Guided Profile Generation (GPG), which generates natural language profiles to summarize key features, resulting in a 37% accuracy improvement in predicting personal preference compared to using raw context.
In modern commercial systems, including Recommendation, Ranking, and E-Commerce platforms, there is a trend towards improving customer experiences by incorporating Personalization context as input into Large Language Models (LLMs). However, LLMs often struggle to effectively parse and utilize sparse and complex personal context without additional processing or contextual enrichment, underscoring the need for more sophisticated context understanding mechanisms. In this work, we propose Guided Profile Generation (GPG), a general method designed to generate personal profiles in natural language. As is observed, intermediate guided profile generation enables LLMs to summarize, and extract the important, distinctive features from the personal context into concise, descriptive sentences, precisely tailoring their generation more closely to an individual's unique habits and preferences. Our experimental results show that GPG improves LLM's personalization ability across different tasks, for example, it increases 37% accuracy in predicting personal preference compared to directly feeding the LLMs with raw personal context.