用自优化微调让大模型更懂推荐，准确率提升37.59%。
Bridging the Gap: Self-Optimized Fine-Tuning for LLM-based Recommender Systems
- 先用自蒸馏生成易学数据，再按难易渐进训练。
- 在真实推荐数据上平均准确率提升37.59%。
- 适合想提升大模型推荐能力的研究者和开发者。
近年来，大型语言模型（LLM）在推荐系统（RS）领域受到广泛关注。当前主要有两种策略使LLM具备推荐能力：1）仅使用提示引导（Guidance-Only），通过上下文学习利用LLM固有的语义理解与推荐能力；2）仅微调（Tuning-Only），通过监督微调（SFT）使LLM适配真实推荐数据。然而，这两种方法均无法有效弥合LLM知识空间与推荐任务之间的差距，性能未达预期。为更好让LLM学习推荐知识，本文结合两者优势，提出一种新型“引导+微调”方法——自优化微调（SOFT），采用课程学习思想：首先通过自蒸馏从微调后的LLM构建一个易于学习但有意义的辅助数据集；随后引入自适应课程调度器，使模型从简单数据（自蒸馏数据）逐步过渡到更具挑战性的真实推荐数据。大量实验表明，SOFT显著提升了基于LLM方法的推荐准确率，平均提升37.59%。代码已公开于 https://anonymous.4open.science/r/Self-Optimized-Fine-Tuning-264E。
原文摘要 · Abstract (English)
Recent years have witnessed extensive exploration of Large Language Models (LLMs) on the field of Recommender Systems (RS). There are currently two commonly used strategies to enable LLMs to have recommendation capabilities: 1) The "Guidance-Only" strategy uses in-context learning to exploit and amplify the inherent semantic understanding and item recommendation capabilities of LLMs; 2) The "Tuning-Only" strategy uses supervised fine-tuning (SFT) to fine-tune LLMs with the aim of fitting them to real recommendation data. However, neither of these strategies can effectively bridge the gap between the knowledge space of LLMs and recommendation, and their performance do not meet our expectations. To better enable LLMs to learn recommendation knowledge, we combine the advantages of the above two strategies and proposed a novel "Guidance+Tuning" method called Self-Optimized Fine-Tuning (SOFT), which adopts the idea of curriculum learning. It first employs self-distillation to construct an auxiliary easy-to-learn but meaningful dataset from a fine-tuned LLM. Then it further utilizes a self-adaptive curriculum scheduler to enable LLMs to gradually learn from simpler data (self-distilled data) to more challenging data (real RS data). Extensive experiments demonstrate that SOFT significantly enhances the recommendation accuracy (37.59\% on average) of LLM-based methods. The code is available via https://anonymous.4open.science/r/Self-Optimized-Fine-Tuning-264E
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。