RecCocktail：一种面向大语言模型推荐的通用高效框架
RecCocktail: A Generalizable and Efficient Framework for LLM-Based Recommendation
AI总结：
针对现有LLM推荐两种范式分离的问题，提出RecCocktail框架，通过熵引导自适应融合通用与领域LoRA模块，兼具通用性与高效性，推理无额外开销，在冷热启动场景均有效。
摘要：
近年来，大语言模型（LLM）凭借出色的泛化能力和丰富的世界知识取得了显著成功。为挖掘LLM作为推荐系统的潜力，主流方法通常聚焦于两种范式：第一种是设计多领域或多任务指令数据以实现通用推荐，从而让LLM适配通用推荐场景并解决冷启动推荐问题；第二种则聚焦于增强特定领域推荐任务，提升热启动推荐场景下的性能。以往大多数研究将这两种范式分开对待，但我们认为二者具有互补优势，结合后能取得更好的效果。\n本文提出了一种通用且高效的基于LLM的推荐框架RecCocktail。该方法首先利用通用领域推荐指令数据微调一个“基酒”LoRA模块，使LLM对齐推荐知识；接着，针对特定领域的用户行为，构建特定领域的“配料”LoRA模块；随后提出一种熵引导的自适应融合方法，在权重空间中混合“基酒”与“配料”。需要注意的是，RecCocktail兼具现有两种范式的优势，且推理阶段不会引入额外的时间或空间开销。此外，RecCocktail具备即插即用的高效性：“基酒”LoRA仅需训练一次，任何特定领域的“配料”都只需通过特定领域微调即可高效完成融合。我们在热启动和冷启动两种推荐场景下的多个数据集上开展了大量实验，结果验证了所提RecCocktail框架的有效性与通用性。
英文摘要：
Large Language Models (LLMs) have achieved remarkable success in recent years, owing to their impressive generalization capabilities and rich world knowledge. To capitalize on the potential of using LLMs as recommender systems, mainstream approaches typically focus on two paradigms. The first paradigm designs multi-domain or multi-task instruction data for generalizable recommendation, so as to align LLMs with general recommendation areas and deal with cold-start recommendation. The second paradigm focuses on enhancing domain-specific recommendation tasks, improving performance in warm recommendation scenarios. While most previous works treat these two paradigms separately, we argue that they have complementary advantages, and combining them can yield better results. In this paper, we propose a generalizable and efficient LLM-based recommendation framework RecCocktail. Our approach begins with fine-tuning a "base spirit" LoRA module using domain-general recommendation instruction data to align LLM with recommendation knowledge. Next, given users' behavior of a specific domain, we construct a domain-specific "ingredient" LoRA module. We then provide an entropy-guided adaptive merging method to mix the "base spirit" and the "ingredient" in the weight space. Please note that, RecCocktail combines the advantages of the existing two paradigms without introducing additional time or space overhead during the inference phase. Moreover, RecCocktail is efficient with plug and play, as the "base spirit" LoRA is trained only once, and any domain-specific "ingredient" can be efficiently mixed with only domain-specific fine-tuning. Extensive experiments on multiple datasets under both warm and cold-start recommendation scenarios validate the effectiveness and generality of the proposed RecCocktail.
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。
