Research
hoBIT: A Profile-Aware Retrieval-Augmented Chatbot for University Academic Advising
arXiv:2608.26604v1 Announce Type: cross Abstract: In university academic advising, identical questions can require different answers depending on a student's department, admission cohort, and degree p
arXiv:2608.26604v1 Announce Type: cross Abstract: 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.
Related
- Not All Retrievals are Useful: Cross-Attention for Input-Aware RAG in Time Series Forecasting
- MEMSAD: Gradient-Coupled Anomaly Detection for Memory Poisoning in Retrieval-Augmented Agents
- Membership Inference Attacks for Retrieval Based In-Context Learning for Document Question Answering
- CleanBase: Detecting Malicious Documents in RAG Knowledge Databases
- Auditing Privacy in Multi-Tenant RAG under Account Collusion
Source: arXiv cs.LG | 2026-08-28