LLMs + Persona-Plug = 個性化的LLMs

摘要

個性化在眾多語言任務和應用中扮演著關鍵角色，因為具有相同需求的用戶可能基於個人興趣而偏好不同的輸出。這導致了各種個性化方法的發展，旨在調整大型語言模型（LLMs）以生成與用戶偏好一致的定制輸出。其中一些方法涉及為每個用戶進行微調以獲得獨特的個性化LLM，但這對於廣泛應用來說成本過高。替代方法以即插即用的方式引入個性化信息，通過檢索用戶的相關歷史文本作為示範。然而，這種基於檢索的策略可能會破壞用戶歷史的連續性，無法捕捉用戶的整體風格和模式，從而導致次優性能。為應對這些挑戰，我們提出了一種新穎的個性化LLM模型。通過輕量級即插即用用戶嵌入模塊對每個個體的所有歷史上下文進行建模，它為每個用戶構建了一個特定的嵌入。通過將此嵌入附加到任務輸入，LLMs能夠更好地理解和捕捉用戶習慣和偏好，從而生成更個性化的輸出，而無需調整其自身參數。在語言模型個性化（LaMP）基準測試中進行的大量實驗表明，所提出的模型明顯優於現有的個性化LLM方法。

English

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, . 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.

LLMs + Persona-Plug = 個性化的LLMs

LLMs + Persona-Plug = Personalized LLMs

摘要

Summary

Support

Support