用自然语言生成用户画像，让大模型更懂个人偏好。
Guided Profile Generation Improves Personalization with LLMs
- 通过引导式生成，将零散用户数据提炼为简洁描述性语句。
- 相比直接输入原始数据，个性化预测准确率提升37%。
- 适合需要精准用户建模的推荐与电商系统。
在现代商业系统（如推荐、排序、电商）中，越来越多地将个性化上下文作为输入融入大型语言模型（LLMs）以提升用户体验。然而，缺乏额外处理或上下文增强时，LLMs 难以有效解析和利用稀疏且复杂的个人上下文，凸显出更先进上下文理解机制的必要性。本文提出一种通用方法——引导式画像生成（Guided Profile Generation, GPG），旨在生成自然语言形式的个人画像。实验表明，中间阶段的引导式画像生成可使 LLMs 更好地总结并提取个人上下文中的重要、独特特征，形成简洁而具描述性的句子，从而更精准地匹配个体习惯与偏好。结果显示，相较于直接输入原始个人上下文，该方法在多个任务中显著提升了个性化能力，例如在预测个人偏好时准确率提升37%。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。