Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2507.03329 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916825625788416 |
|---|---|
| author | Patel, Devendra Jain, Aaditya Verma, Jayant Rajput, Divyansh Mahala, Sunil Khapare, Ketki Suresh Kalla, Jayateja |
| author_facet | Patel, Devendra Jain, Aaditya Verma, Jayant Rajput, Divyansh Mahala, Sunil Khapare, Ketki Suresh Kalla, Jayateja |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_03329 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | NDAI-NeuroMAP: A Neuroscience-Specific Embedding Model for Domain-Specific Retrieval Patel, Devendra Jain, Aaditya Verma, Jayant Rajput, Divyansh Mahala, Sunil Khapare, Ketki Suresh Kalla, Jayateja Artificial Intelligence 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. |
| title | NDAI-NeuroMAP: A Neuroscience-Specific Embedding Model for Domain-Specific Retrieval |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2507.03329 |