面向个性化推荐的大语言模型因果增强行为序列建模
Causality-Enhanced Behavior Sequence Modeling in LLMs for Personalized Recommendation
AI总结：
针对大语言模型在个性化推荐中难以充分利用用户行为序列的问题，提出反事实微调方法，通过因果推理显式强化行为序列作用并结合令牌级加权机制，有效提升了推荐中的行为序列建模效果。
摘要：
推荐系统领域的最新研究聚焦于利用大语言模型（LLMs）改进用户偏好建模，已取得可观成果。然而，当前基于LLM的方法难以充分利用用户行为序列，导致个性化推荐的偏好建模效果欠佳。本研究提出一种新颖的反事实微调（Counterfactual Fine-Tuning，CFT）方法，通过在生成推荐时显式强化行为序列的作用来解决这一问题。具体而言，我们采用反事实推理识别行为序列对模型输出的因果效应，并引入一项基于这些效应直接拟合真实标签的任务，实现显式强化的目标。此外，我们开发了一种令牌级加权机制，用于调整不同物品令牌的强化强度，以反映在预测物品时行为序列的影响从早期令牌到后期令牌逐渐减弱的规律。在真实世界数据集上开展的大量实验表明，CFT有效提升了行为序列建模效果。我们的代码可在https://github.com/itsmeyjt/CFT获取。
英文摘要：
Recent advancements in recommender systems have focused on leveraging Large Language Models (LLMs) to improve user preference modeling, yielding promising outcomes. However, current LLM-based approaches struggle to fully leverage user behavior sequences, resulting in suboptimal preference modeling for personalized recommendations. In this study, we propose a novel Counterfactual Fine-Tuning (CFT) method to address this issue by explicitly emphasizing the role of behavior sequences when generating recommendations. Specifically, we employ counterfactual reasoning to identify the causal effects of behavior sequences on model output and introduce a task that directly fits the ground-truth labels based on these effects, achieving the goal of explicit emphasis. Additionally, we develop a token-level weighting mechanism to adjust the emphasis strength for different item tokens, reflecting the diminishing influence of behavior sequences from earlier to later tokens during predicting an item. Extensive experiments on real-world datasets demonstrate that CFT effectively improves behavior sequence modeling. Our codes are available at https://github.com/itsmeyjt/CFT.
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。
