Large Language Models (LLMs), such as GPT3.5, have exhibited remarkable proficiency in comprehending and generating natural language. However, their unpersonalized generation paradigm may result in suboptimal user-specific outcomes. Typically, users converse differently based on their knowledge and preferences. This necessitates the task of enhancing user-oriented LLM which remains unexplored. While one can fully train an LLM for this objective, the resource consumption is unaffordable. Prior research has explored memory-based methods to store and retrieve knowledge to enhance generation without retraining for new queries. However, we contend that a mere memory module is inadequate to comprehend a user's preference, and fully training an LLM can be excessively costly. In this study, we propose a novel computational bionic memory mechanism, equipped with a parameter-efficient fine-tuning schema, to personalize LLMs. Our extensive experimental results demonstrate the effectiveness and superiority of the proposed approach. To encourage further research into this area, we are releasing a new conversation dataset generated entirely by LLM based on an open-source medical corpus, as well as our implementation code.

翻译：大语言模型（如GPT3.5）在理解和生成自然语言方面表现出卓越的能力。然而，其非个性化的生成范式可能导致针对用户特定需求的次优结果。通常，用户会根据自身知识和偏好以不同方式进行对话，这要求我们探索尚未充分研究的用户导向型大语言模型增强任务。虽然可以通过完整训练大语言模型实现该目标，但资源消耗难以承受。现有研究探索了基于记忆的方法来存储和检索知识，从而在不重新训练的情况下增强针对新查询的生成能力。但我们认为，单纯的记忆模块不足以理解用户偏好，而完整训练大语言模型又过于昂贵。本研究提出一种新型计算仿生记忆机制，结合参数高效微调策略，实现大语言模型的个性化。大量实验结果表明了所提方法的有效性与优越性。为促进该领域的进一步研究，我们基于开源医学语料库发布了一个完全由大语言模型生成的新对话数据集及实现代码。