Dreams：基于双节点蒙特卡洛树搜索的对话推荐系统上下文建模
原标题：Towards Effective Structured Context Modeling for Conversational Recommender Systems via Dual-node Monte Carlo Tree Search
AI 摘要
arXiv 论文提出 Dreams，一种用于对话推荐系统（CRS）的双节点树结构上下文建模框架。Dreams 通过蒙特卡洛树搜索（MCTS）进行偏好 elicitation，并使用 LLM 将偏好状态转化为结构化检索查询以实现 exploitation。实验证明其在基准数据集上优于现有方法，代码已开源。
正文节选
Towards Effective Structured Context Modeling for Conversational Recommender Systems via Dual-node Monte Carlo Tree Search Abstract We investigate the role of conversational context modeling in user preference tracking for Conversational Recommendation Systems (CRSs). In this regard, we propose Dreams, a novel tree-structured context modeling framework that explicitly captures user preference evolution throughout multi-turn interactions. Dreams introduces two specialized node types to support th