Year: 2025
Type: preprint
Abstract: We present NDAI-NeuroMAP, the first neuroscience-domain-specific dense vector embedding model engineered for high-precision information retrieval tasks. Our methodology encompasses the curation of an extensive domain-specific training corpus comprising 500,000 carefully constructed triplets (query-positive-negative configurations), augmented with 250,000 neuroscience-specific definitional entries and 250,000 structured knowledge-graph triplets derived from authoritative neurological ontologies. We employ a sophisticated fine-tuning approach utilizing the FremyCompany/BioLORD-2023 foundation model, implementing a multi-objective optimization framework combining contrastive learning with triplet-based metric learning paradigms. Comprehensive evaluation on a held-out test dataset comprising approximately 24,000 neuroscience-specific queries demonstrates substantial performance improvements over state-of-the-art general-purpose and biomedical embedding models. These empirical findings underscore the critical importance of domain-specific embedding architectures for neuroscience-oriented RAG systems and related clinical natural language processing applications.
Source: arXiv (Cornell University)
Authors: Patel, Devendra, Jain, Aaditya, Verma, Jayant, Rajput, Divyansh, Mahala, Sunil, Khapare, Ketki Suresh, Kalla, Jayateja
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4415162383
Cites:
Cited by:
Related to: