Re2A：基于评分标准偏好推理与对齐的情境化对话推荐
Re2A: Situated Conversational Recommendation via Rubric-based Preference Reasoning and Alignment
浏览论文内容
中文总结 AI 辅助
针对情境化对话推荐中偏好理解与响应生成的挑战，提出Re2A框架，通过基于评分标准的偏好推理和偏好条件优化，实现用户偏好与情境一致性的双重对齐，实验验证其优于现有方法。
中文摘要 AI 辅助
真实世界的推荐场景通常发生在用户与推荐系统交互过程中共享的物理环境中。这推动了情境化对话推荐（SCR）的发展，这是一项复杂的任务，要求推荐助手同时推理对话历史、共同观察到的场景以及场景内的物品属性。然而，当前的方法在这一设定下面临两个相互交织的挑战：在对话过程中准确理解情境化的用户偏好，以及生成同时满足用户需求和情境约束的响应。为此，我们提出了Re2A，一个将SCR形式化为结构化“先推理后对齐”过程的框架。我们引入了基于评分标准的偏好推理，利用自动化评分标准引导模型生成明确的偏好状态。基于这些状态，我们提出了一种偏好条件优化方法，使响应生成与双重目标对齐：用户偏好满足和情境一致性。在两个SCR数据集上的大量实验表明，Re2A持续优于最先进的方法，提供了更精确、更具上下文感知的对话推荐。我们的代码可在该https URL获取。
英文摘要
Real-world recommendation scenarios are commonly grounded in shared physical environments during user-recommender interactions. This motivates situated conversational recommendation (SCR), a complex task requiring recommender assistants to jointly reason over dialogue history, co-observed scenes, and in-scene item attributes. However, current approaches struggle with this setting due to two intertwined challenges: accurately understanding situated user preferences throughout the conversation and generating responses that simultaneously satisfy user needs and grounded situations. To this end, we propose Re2A, a framework that formulates SCR as a structured reason-then-align process. We introduce rubric-based preference reasoning, which uses automated rubrics to guide the model toward producing explicit preference states. Based on these states, we propose a preference-conditioned optimization to align response generation with dual objectives: user preference satisfaction and situation consistency. Extensive experiments on two SCR datasets demonstrate that Re2A consistently outperforms state-of-the-art methods, delivering more precise, context-aware conversational recommendations. Our code is available at https://github.com/DongdingLin/Re2A.
发表机构
- The Hong Kong Polytechnic University（香港理工大学）
- The Chinese University of Hong Kong（香港中文大学）
- Sichuan University（四川大学）
机构由 AI 辅助整理，请以论文原文为准。
