让大模型学会记住用户对话，实现更个性化的回复。
On the Way to LLM Personalization: Learning to Remember User Conversations
- 通过对话序列数据增强生成问答对，训练低秩适配器。
- 在100次对话上达到81.5%的准确率，媲美RAG方法。
- 适合需要轻量级个性化的大模型应用开发。
大型语言模型（LLMs）已迅速成为多种任务的宝贵助手，但其效果受限于个性化能力——即根据用户偏好和行为调整回应。现有研究主要集中在风格迁移或注入少量用户事实信息，而知识注入仍是一个开放挑战。本文探索将历史对话知识注入大模型，以支持未来更少重复、更具个性化的对话。我们识别出两个现实约束：(1) 对话具有时间顺序性，训练时必须保持该特性；(2) 个性化需在参数高效设置下实现。为此，我们提出PLUM，一个先对对话进行数据增强以生成问答对，再用加权交叉熵损失微调低秩适配器的流程。即使在首次探索此问题的情况下，其表现仍可与RAG等基线方法媲美，在100次对话中达到81.5%的准确率。
原文摘要 · Abstract (English)
Large Language Models (LLMs) have quickly become an invaluable assistant for a variety of tasks. However, their effectiveness is constrained by their ability to tailor responses to human preferences and behaviors via personalization. Prior work in LLM personalization has largely focused on style transfer or incorporating small factoids about the user, as knowledge injection remains an open challenge. In this paper, we explore injecting knowledge of prior conversations into LLMs to enable future work on less redundant, personalized conversations. We identify two real-world constraints: (1) conversations are sequential in time and must be treated as such during training, and (2) per-user personalization is only viable in parameter-efficient settings. To this aim, we propose PLUM, a pipeline performing data augmentation for up-sampling conversations as question-answer pairs, that are then used to finetune a low-rank adaptation adapter with a weighted cross entropy loss. Even in this first exploration of the problem, we perform competitively with baselines such as RAG, attaining an accuracy of 81.5% across 100 conversations.
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。