走向大语言模型个性化：学习记住用户对话
On the Way to LLM Personalization: Learning to Remember User Conversations
AI总结：
本文提出PLUM流程，通过将用户历史对话增强为问答对并微调低秩适配器，以参数高效方式向大语言模型注入对话知识，在100个对话上取得81.5%准确率，性能与RAG相当。
摘要：
大语言模型（LLMs）已迅速成为各类任务中不可或缺的助手。然而，其有效性受限于通过个性化来调整响应以符合人类偏好和行为的能力。此前关于LLM个性化的研究主要集中在风格迁移或注入关于用户的小型事实片段上，因为知识注入仍然是一个尚未解决的挑战。在本文中，我们探索将先前对话的知识注入LLMs，以便为未来减少冗余、实现个性化对话的工作奠定基础。我们识别出两个现实约束：（1）对话在时间上是顺序进行的，在训练过程中必须如此对待；（2）按用户进行个性化仅在参数高效设置下才可行。为此，我们提出PLUM，这是一个执行数据增强的流程，将对话上采样为问答对，然后使用加权交叉熵损失对低秩适配（low-rank adaptation）适配器进行微调。即使在对该问题的首次探索中，我们的表现也与RAG等基线方法具有竞争力，在100个对话上达到了81.5%的准确率。
英文摘要：
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.
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。
