通过对比用户偏好提升对话推荐效果
Empowering Retrieval-based Conversational Recommendation with Contrasting User Preferences
- 用大模型推理生成用户潜在偏好并区分喜好与厌恶
- 在三个基准数据集上，Recall@10最高提升99.72%
- 适合需要精准捕捉用户矛盾意图的推荐场景
对话式推荐系统（CRS）通过多轮对话为用户推荐其可能偏好的目标项目。近期研究强调捕捉用户对话中的情感可提升推荐准确性，但普遍采用单一用户表征，难以区分用户对立意图（如喜欢与不喜欢），可能导致性能不佳。为此，本文提出新模型CORAL（COntrasting user pReference expAnsion and Learning）。首先，CORAL利用大语言模型的推理能力，通过对比偏好扩展提取用户的隐含偏好；其次，基于潜在偏好显式区分对立偏好，并通过偏好感知学习融入推荐过程。大量实验表明，CORAL在三个基准数据集上显著优于现有方法，Recall@10最高提升99.72%。代码与数据集已开源。
原文摘要 · Abstract (English)
Conversational recommender systems (CRSs) are designed to suggest the target item that the user is likely to prefer through multi-turn conversations. Recent studies stress that capturing sentiments in user conversations improves recommendation accuracy. However, they employ a single user representation, which may fail to distinguish between contrasting user intentions, such as likes and dislikes, potentially leading to suboptimal performance. To this end, we propose a novel conversational recommender model, called COntrasting user pReference expAnsion and Learning (CORAL). Firstly, CORAL extracts the user's hidden preferences through contrasting preference expansion using the reasoning capacity of the LLMs. Based on the potential preference, CORAL explicitly differentiates the contrasting preferences and leverages them into the recommendation process via preference-aware learning. Extensive experiments show that CORAL significantly outperforms existing methods in three benchmark datasets, improving up to 99.72% in Recall@10. The code and datasets are available at https://github.com/kookeej/CORAL
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。