[
    {
        "id": "osp-16435",
        "type": "article-journal",
        "title": "BioBigBird: A Sparse Attention Model for Long-Range Dependency Processing in Biomedical Text",
        "author": [
            {
                "family": "Balaji",
                "given": "Roshan"
            },
            {
                "family": "S",
                "given": "Pavan Kumar"
            },
            {
                "family": "Gupta",
                "given": "Vasudev"
            },
            {
                "family": "N",
                "given": "Sreejith"
            },
            {
                "family": "Sridhar",
                "given": "Keerthana"
            },
            {
                "family": "Bhatt",
                "given": "Nirav"
            }
        ],
        "URL": "https://omanscience.com/en/articles/biobigbird-a-sparse-attention-model-for-long-range-dependency-processing-in-biomedical-text",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "abstract": "While domain-specific Large Language Models (LLMs) have encoded vast biomedical knowledge, their limited context windows often hinder a deep understanding of nuanced relationships within and across texts. To address this limitation, we introduce BioBigBird, a bidirectional language model pre-trained on extensive biomedical literature and clinical data, specifically designed to handle long-range dependencies. BioBigBird leverages a sparse attention mechanism to process sequences up to 4096 tokens, and its training incorporates a multi-stage process to mitigate noise from the large-scale pre-training corpus. We further enhance its performance by employing a multi-task learning (MTL) framework that jointly optimizes for Named Entity Recognition and Relation Extraction. Comprehensive evaluations on the BLURB benchmark reveal that our MTL-enhanced BioBigBird achieves highly competitive results against state-of-the-art models. Our work contributes an effective methodology for developing powerful, long-context language models for specialized domains, demonstrating the value of extended sequence processing for complex text analysis. Our models are publicly available at https://huggingface.co/collections/bisectgroup/biobigbird."
    }
]