{"ID":2837824,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.19739","arxiv_id":"2511.19739","title":"Comparative Analysis of LoRA-Adapted Embedding Models for Clinical Cardiology Text Representation","abstract":"Domain-specific text embeddings are critical for clinical natural language processing, yet systematic comparisons across model architectures remain limited. This study evaluates ten transformer-based embedding models adapted for cardiology through Low-Rank Adaptation (LoRA) fine-tuning on 106,535 cardiology text pairs derived from authoritative medical textbooks. Results demonstrate that encoder-only architectures, particularly BioLinkBERT, achieve superior domain-specific performance (separation score: 0.510) compared to larger decoder-based models, while requiring significantly fewer computational resources. The findings challenge the assumption that larger language models necessarily produce better domain-specific embeddings and provide practical guidance for clinical NLP system development. All models, training code, and evaluation datasets are publicly available to support reproducible research in medical informatics.","short_abstract":"Domain-specific text embeddings are critical for clinical natural language processing, yet systematic comparisons across model architectures remain limited. This study evaluates ten transformer-based embedding models adapted for cardiology through Low-Rank Adaptation (LoRA) fine-tuning on 106,535 cardiology text pairs...","url_abs":"https://arxiv.org/abs/2511.19739","url_pdf":"https://arxiv.org/pdf/2511.19739v1","authors":"[\"Richard J. Young\",\"Alice M. Matthews\"]","published":"2025-11-24T21:57:09Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.LG\"]","methods":"[\"Transformer\",\"Language Model\",\"LoRA\"]","has_code":false}