让大学顾问机器人读懂学生背景，精准回答个性化问题。
hoBIT: A Profile-Aware Retrieval-Augmented Chatbot for University Academic Advising
- 根据问题动态获取必要学生信息，精准检索答案
- 在多个评测中优于现有RAG方法，用户更偏好
- 支持低成本本地部署，适合高校实际场景
在大学学术咨询中，相同问题因学生所属院系、入学年份和学位项目不同而需不同回答，导致不考虑用户背景的检索系统常返回看似合理但不适用的信息。本文提出proFILL，将作者所在学院现有的基于规则的咨询聊天机器人hoBIT升级为具备用户画像感知能力的检索增强生成（RAG）系统。proFILL无需一次性获取完整用户资料，而是根据查询意图和初始检索结果，逐步获取当前所需的学生属性，并用于在带有画像感知索引的数据库中进行条件化检索。大量实验与人工偏好研究显示，proFILL在多个基准上表现优于多种RAG基线模型，被目标用户更青睐，且在使用开源大模型时仍保持高效，适用于成本敏感的本地部署场景。
原文摘要 · Abstract (English)
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.
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。