H-MAPS: Hierarchical Memory-Augmented Proactive Search Assistant for Scientific Literature
Koji Nishikawa, Makoto P. Kato
TLDR
H-MAPS is a proactive search assistant that uses hierarchical memory to provide personalized literature recommendations, reducing cognitive load during scientific reading.
Key contributions
- Uses a three-layered hierarchical memory to resolve context ambiguity in proactive search.
- Articulates user's latent information needs into explicit natural language questions.
- Performs neural retrieval entirely on the local device, ensuring user privacy.
- Delivers personalized literature tailored to specific user profiles and backgrounds.
Why it matters
Scientific reading often requires external resources, but current search methods are disruptive and lack personalization. H-MAPS addresses this by proactively offering relevant, context-aware literature. This enhances the reading experience and reduces cognitive load for researchers.
Original Abstract
Scientific reading is an active process that frequently requires consulting external resources, but manual keyword searching interrupts the reading flow and imposes a high cognitive load. Existing proactive information retrieval systems often suffer from context ambiguity, as they rely solely on on-screen text and ignore the reader's specific background and intent. In this demonstration, we present H-MAPS (Hierarchical Memory-Augmented Proactive Search Assistant), a proactive literature exploration assistant that resolves this ambiguity by leveraging a three-layered hierarchical memory. Triggered by implicit reading behaviors, H-MAPS articulates the user's latent information needs into explicit natural language questions and performs neural retrieval entirely on the local device to ensure privacy. We demonstrate H-MAPS using a scenario where two researchers, specializing in NLP and HCI, read the same paper. In response, the system generates profile-specific questions and retrieves distinct literature tailored to each user.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.