LaMP：当大型语言模型遇上个性化
LaMP: When Large Language Models Meet Personalization
AI总结：
本文提出 LaMP 基准，用于训练和评估大语言模型生成个性化输出，并设计了两种检索增强方法，实验证明其有效性和个性化对自然语言任务的影响。
摘要：
本文强调了大型语言模型中个性化的重要性，并引入了 LaMP 基准——一个用于训练和评估语言模型以生成个性化输出的新型基准。LaMP 提供了一个全面的评估框架，包含多样化的语言任务和每个用户配置文件的多个条目。它由七个个性化任务组成，涵盖三个文本分类和四个文本生成任务。我们还提出了两种检索增强方法，从每个用户配置文件中检索个人项目以个性化语言模型输出。为此，我们研究了各种检索模型，包括术语匹配、语义匹配和时间感知方法。在 LaMP 上对零样本和微调语言模型进行的广泛实验证明了所提出的检索增强方法的有效性，并突显了个性化在各种自然语言任务中的影响。
英文摘要：
This paper highlights the importance of personalization in large language models and introduces the LaMP benchmark -- a novel benchmark for training and evaluating language models for producing personalized outputs. LaMP offers a comprehensive evaluation framework with diverse language tasks and multiple entries for each user profile. It consists of seven personalized tasks, spanning three text classification and four text generation tasks. We additionally propose two retrieval augmentation approaches that retrieve personal items from each user profile for personalizing language model outputs. To this aim, we study various retrieval models, including term matching, semantic matching, and time-aware methods. Extensive experiments on LaMP for zero-shot and fine-tuned language models demonstrate the efficacy of the proposed retrieval augmentation approach and highlight the impact of personalization in various natural language tasks.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
