← Back to all news
arXiv Machine Learning By Yoonseo Kim, Seongmin Lee, Joongheon Kim, SeongKu Kang

hoBIT: A Profile-Aware Retrieval-Augmented Chatbot for University Academic Advising

Read the original on arXiv Machine Learning →

The paper introduces proFILL, a method that transforms the existing rule-based advising chatbot hoBIT into a profile-aware retrieval-augmented generation system. Instead of needing a full student profile at the start, proFILL incrementally gathers only the attributes required for each query, using both the query intent and initially retrieved evidence to guide retrieval from a profile-aware index. Experiments and a human preference study demonstrate that proFILL outperforms various RAG baselines, is favored by users, and remains effective when deployed with open-weight models for cost-efficient on‑premise use.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Sep 4

Comparing Retrieval Methods for Academic Advisor Discovery: A Six-Method Study of 768 CS Faculty Profiles Across 9 US Universities

The study evaluates six retrieval methods for ranking computer science faculty as potential academic advisors based on graduate applicants’ research interest statements. Using a new dataset of 768 faculty profiles from nine U.S. universities and 162 graded relevance judgments across five queries, the reranked hybrid approach achieved the highest mean NDCG@10 (0.477). Ablation experiments showed that faculty biographies alone outperform the full model, and adding arXiv abstracts actually decreased performance, leading to a late‑fusion design. All code, data, and labels are publicly released.

By Biraj Subedi
ragbenchmarks
More like this →
arXiv AI
Jun 2

NBQ: Next-Best-Question for Dynamic Profiling

arXiv:2606. 00809v1 Announce Type: new Abstract: Many real-world conversational settings for knowledge discovery, including podcasts, hiring screens, and marketplaces, require a purpose-driven understanding of a person.

By Yimin Shi, Clarice Wang, Haixun Wang, Xiaokui Xiao
rag
More like this →
arXiv Computation and Language
Sep 4

Bounded Personas Match Retrieval on Classification but Not Regression for a Frozen Agent

The paper introduces PersonaLink, a training‑free method that distills a user’s interaction history into a bounded three‑field persona and iteratively refines it by self‑evaluating a frozen 7B language model on held‑out labeled data. Each refinement rewrites the persona only if it does not regress on that slice, ensuring the persona remains bounded and query‑independent. On a 200‑user news categorization task (LaMP‑2), PersonaLink achieves 0.745–0.755 accuracy, statistically indistinguishable from BM25 retrieval’s 0.760–0.765 accuracy, demonstrating that distilled personas can match retrieval for classification but not for regression tasks.

By JaeHa Yoon, Minjun Park, Seoyeon Kim, Jiwoo Lee, Hyunwoo Choi, Dohyun Kang
agentsefficiency
More like this →