Guided Profile Generation Improves Personalization with LLMs

TL;DR

This paper introduces Guided Profile Generation (GPG), a method that enhances LLMs' ability to personalize by creating concise personal profiles, significantly improving prediction accuracy in personalization tasks.

Contribution

The paper presents GPG, a novel approach for generating natural language personal profiles that improve LLMs' understanding and utilization of personal context for better personalization.

Findings

GPG increases personalization accuracy by 37%.

Intermediate profile generation helps LLMs extract key personal features.

GPG improves performance across different personalization tasks.

Abstract

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.