arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2404.05970cs.CLcs.IR
收藏

通过检索增强个性化大型语言模型的优化方法

Optimization Methods for Personalizing Large Language Models through Retrieval Augmentation

University of Massachusetts Amherst(马萨诸塞大学阿默斯特分校)

Alireza Salemi, Surya Kallumadi, Hamed Zamani

AI总结:

本文提出通过强化学习和知识蒸馏优化检索模型,并引入检索器选择模型,在LaMP基准上显著提升个性化生成性能。

摘要:

本文研究了检索增强方法用于个性化大型语言模型(LLM),这可能在各种应用和领域产生重大影响。我们首次尝试优化检索模型,该模型向大型语言模型提供有限数量的个人文档,以实现个性化生成。我们开发了两种优化算法,从下游个性化生成任务中获取反馈以进行检索优化——一种基于强化学习,其奖励函数使用任意个性化生成指标定义;另一种基于从下游LLM到检索模型的知识蒸馏。本文还引入了一个生成前和生成后的检索器选择模型,该模型决定为每个LLM输入选择哪个检索器。在语言模型个性化(LaMP)基准的多样化任务上进行的大量实验显示,在七个数据集中的六个上取得了统计显著的改进。

英文摘要:

This paper studies retrieval-augmented approaches for personalizing large language models (LLMs), which potentially have a substantial impact on various applications and domains. We propose the first attempt to optimize the retrieval models that deliver a limited number of personal documents to large language models for the purpose of personalized generation. We develop two optimization algorithms that solicit feedback from the downstream personalized generation tasks for retrieval optimization -- one based on reinforcement learning whose reward function is defined using any arbitrary metric for personalized generation and another based on knowledge distillation from the downstream LLM to the retrieval model. This paper also introduces a pre- and post-generation retriever selection model that decides what retriever to choose for each LLM input. Extensive experiments on diverse tasks from the language model personalization (LaMP) benchmark reveal statistically significant improvements in six out of seven datasets.

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。

↑