发表机构
Korea University（高丽大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对大学学术咨询中因用户画像缺失导致的检索证据不适用问题，提出proFILL方法将hoBIT转换为感知用户画像的RAG系统，实验显示其性能优于多种基线且受用户偏好，可低成本本地部署。
AI 中文摘要
在大学学术咨询场景中，相同问题的答案会因学生的院系、入学批次和学位项目不同而存在差异，这会导致不感知用户画像的检索器返回看似合理但并不适用的证据。我们提出proFILL方法，将本校当前基于规则的咨询聊天机器人hoBIT转换为感知用户画像的检索增强生成（RAG）系统。proFILL无需用户提前提供完整画像，而是基于查询意图和初始检索到的证据，逐步获取每个查询所需的画像属性，并利用这些属性在感知用户画像的索引上进行条件检索。大量实验和人类偏好研究表明，proFILL在多种RAG基线中表现更优，受到目标用户的偏好，且在使用开源权重模型时仍能保持有效，适用于成本效益高的本地部署。
英文摘要
In university academic advising, identical questions can require different answers depending on a student's department, admission cohort, and degree program, causing profile-blind retrievers to surface plausible but inapplicable evidence. We present proFILL, a method for transforming hoBIT, our college's current rule-based advising chatbot, into a profile-aware retrieval-augmented generation (RAG) system. Rather than requiring a complete user profile upfront, proFILL progressively acquires only the profile attributes needed for each query, guided by both the query intent and the initially retrieved evidence, and uses them to condition retrieval over a profile-aware index. Extensive experiments and a human preference study show that proFILL outperforms diverse RAG baselines, is preferred by target users, and remains effective with open-weight models for cost-effective on-premise deployment.
CommentsAccepted to the System Demonstrations Track at EMNLP 2026
