面向不同用户相同查询生成定制化回复的个性化大语言模型
Personalized LLM for Generating Customized Responses to the Same Query from Different Users
AI总结：
本文提出查询者感知的LLM个性化方法，通过双塔编码器和聚类约束的对比学习，使同一查询对不同用户生成不同回复，并构建MQDialog数据集验证了回复质量的显著提升。
摘要：
现有的大语言模型（LLM）个性化工作为LLM分配了不同的回复角色，但忽视了查询者的多样性。在本工作中，我们提出了一种新的查询者感知的LLM个性化形式，即使对于来自不同查询者的相同查询，也能生成不同的回复。我们设计了一种双塔模型架构，包含一个跨查询者通用编码器和一个查询者特定编码器。我们进一步应用带有多视图增强的对比学习，拉近同一查询者的对话表示，同时拉远不同查询者的对话表示。为了减轻查询多样性对查询者对比学习的影响，我们基于查询相似性对对话进行聚类，并将对比学习的范围限制在每个聚类内部。为了解决缺乏为查询者感知个性化设计的数据集的问题，我们还从英文和中文剧本以及微信记录中构建了一个多查询者数据集，称为MQDialog，包含173个查询者和12个回复者。大量评估表明，我们的设计显著提高了定制化回复生成的质量，与各种基线方法相比，ROUGE-L分数实现了8.4%至48.7%的相对提升，胜率在54%至82%之间。
英文摘要：
Existing work on large language model (LLM) personalization assigned different responding roles to LLMs, but overlooked the diversity of queriers. In this work, we propose a new form of querier-aware LLM personalization, generating different responses even for the same query from different queriers. We design a dual-tower model architecture with a cross-querier general encoder and a querier-specific encoder. We further apply contrastive learning with multi-view augmentation, pulling close the dialogue representations of the same querier, while pulling apart those of different queriers. To mitigate the impact of query diversity on querier-contrastive learning, we cluster the dialogues based on query similarity and restrict the scope of contrastive learning within each cluster. To address the lack of datasets designed for querier-aware personalization, we also build a multi-querier dataset from English and Chinese scripts, as well as WeChat records, called MQDialog, containing 173 queriers and 12 responders. Extensive evaluations demonstrate that our design significantly improves the quality of personalized response generation, achieving relative improvement of 8.4% to 48.7% in ROUGE-L scores and winning rates ranging from 54% to 82% compared with various baseline methods.
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。
