LLMs + Persona-Plug = 个性化大语言模型
LLMs + Persona-Plug = Personalized LLMs
AI总结：
提出一种轻量级插件式用户嵌入模块PPersona-Plug，通过建模用户历史上下文生成个性化嵌入，无需微调即可提升大语言模型输出个性化程度。
摘要：
个性化在众多语言任务和应用中扮演着关键角色，因为具有相同需求的用户可能根据个人兴趣偏好不同的输出。这促使了各种个性化方法的发展，旨在使大语言模型（LLMs）适应生成符合用户偏好的定制化输出。其中一些方法涉及为每个用户微调一个独特的个性化LLM，这过于昂贵而难以广泛应用。替代方法以即插即用的方式引入个性化信息，通过检索用户相关历史文本作为示例。然而，这种基于检索的策略可能会破坏用户历史的连续性，无法捕捉用户的整体风格和模式，从而导致次优性能。为了解决这些挑战，我们提出了一种新颖的个性化LLM模型PPersona-Plug。它通过一个轻量级的插件式用户嵌入模块，对每个用户的所有历史上下文进行建模，构建用户特定的嵌入。通过将该嵌入附加到任务输入中，LLMs可以更好地理解和捕捉用户的习惯与偏好，从而在不调整自身参数的情况下生成更个性化的输出。在语言模型个性化（LaMP）基准上的各种任务上的大量实验表明，所提出的模型显著优于现有的个性化LLM方法。
英文摘要：
Personalization plays a critical role in numerous language tasks and applications, since users with the same requirements may prefer diverse outputs based on their individual interests. This has led to the development of various personalized approaches aimed at adapting large language models (LLMs) to generate customized outputs aligned with user preferences. Some of them involve fine-tuning a unique personalized LLM for each user, which is too expensive for widespread application. Alternative approaches introduce personalization information in a plug-and-play manner by retrieving the user's relevant historical texts as demonstrations. However, this retrieval-based strategy may break the continuity of the user history and fail to capture the user's overall styles and patterns, hence leading to sub-optimal performance. To address these challenges, we propose a novel personalized LLM model, PPlug. It constructs a user-specific embedding for each individual by modeling all her historical contexts through a lightweight plug-in user embedder module. By attaching this embedding to the task input, LLMs can better understand and capture user habits and preferences, thereby producing more personalized outputs without tuning their own parameters. Extensive experiments on various tasks in the language model personalization (LaMP) benchmark demonstrate that the proposed model significantly outperforms existing personalized LLM approaches.
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。
