NDAI-NeuroMAP: A Neuroscience-Specific Embedding Model for Domain-Specific Retrieval
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.
Cite
@article{arxiv.2507.03329,
title = {NDAI-NeuroMAP: A Neuroscience-Specific Embedding Model for Domain-Specific Retrieval},
author = {Devendra Patel and Aaditya Jain and Jayant Verma and Divyansh Rajput and Sunil Mahala and Ketki Suresh Khapare and Jayateja Kalla},
journal= {arXiv preprint arXiv:2507.03329},
year = {2025}
}
Comments
The document consists of 15 pages in total: the first 13 pages comprise the main paper, while the last two pages contain supplementary material