迈向有效的LLM个性化模型编辑
Towards Effective Model Editing for LLM Personalization
AI总结：
本文提出个性化编辑框架，通过聚类偏好表示实现高效LLM个性化，提升多轮交互和隐含查询的性能。
摘要：
个性化正变得不可或缺，使LLM能够与个体用户偏好和需求对齐。然而，当前的方法往往计算成本高、数据需求大、容易出现灾难性遗忘，并且在多轮交互或处理隐含查询时容易性能下降。为了解决这些挑战，我们将个性化概念化为一个模型编辑任务，并引入个性化编辑，一种通过聚类的偏好表示引导的局部编辑框架。这种设计使能够实现精确的偏好对齐更新，同时保持整体模型能力。此外，现有的个性化基准测试经常依赖于LLM之间的基于角色的对话，而不是用户与LLM的交互，或者主要关注风格模仿，而忽视了需要准确回忆用户特定偏好的信息检索任务。我们引入了用户偏好问答（UPQA），一个由现场用户查询构建的简短问答数据集，具有不同难度级别。与之前的基准测试不同，UPQA直接评估模型回忆和应用特定用户偏好的能力。在各种实验设置中，个性化编辑在编辑准确性和计算效率方面均优于微调，同时在多轮对话和隐含偏好问题设置中优于基于提示的基线。
英文摘要：
Personalization is becoming indispensable for LLMs to align with individual user preferences and needs. Yet current approaches are often computationally expensive, data-intensive, susceptible to catastrophic forgetting, and prone to performance degradation in multi-turn interactions or when handling implicit queries. To address these challenges, we conceptualize personalization as a model editing task and introduce Personalization Editing, a framework that applies localized edits guided by clustered preference representations. This design enables precise preference-aligned updates while preserving overall model capabilities. In addition, existing personalization benchmarks frequently rely on persona-based dialogs between LLMs rather than user-LLM interactions, or focus primarily on stylistic imitation while neglecting information-seeking tasks that require accurate recall of user-specific preferences. We introduce User Preference Question Answering (UPQA), a short-answer QA dataset constructed from in-situ user queries with varying levels of difficulty. Unlike prior benchmarks, UPQA directly evaluates a model's ability to recall and apply specific user preferences. Across experimental settings, Personalization Editing achieves higher editing accuracy and greater computational efficiency than fine-tuning, while outperforming prompting-based baselines in multi-turn conversations and implicit preference questions settings.
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。
