Large Language Models (LLMs) have swiftly emerged as vital resources for different applications in the biomedical and healthcare domains; however, these models encounter issues such as generating inaccurate information or hallucinations. Retrieval-augmented generation provided a solution for these models to update knowledge and enhance their performance. In contrast to previous retrieval-augmented LMs, which utilize specialized cross-attention mechanisms to help LLM encode retrieved text, BiomedRAG adopts a simpler approach by directly inputting the retrieved chunk-based documents into the LLM. This straightforward design is easily applicable to existing retrieval and language models, effectively bypassing noise information in retrieved documents, particularly in noise-intensive tasks. Moreover, we demonstrate the potential for utilizing the LLM to supervise the retrieval model in the biomedical domain, enabling it to retrieve the document that assists the LM in improving its predictions. Our experiments reveal that with the tuned scorer,\textsc{ BiomedRAG} attains superior performance across 5 biomedical NLP tasks, encompassing information extraction (triple extraction, relation extraction), text classification, link prediction, and question-answering, leveraging over 9 datasets. For instance, in the triple extraction task, \textsc{BiomedRAG} outperforms other triple extraction systems with micro-F1 scores of 81.42 and 88.83 on GIT and ChemProt corpora, respectively.

翻译：大型语言模型（LLMs）已迅速成为生物医学与医疗领域多种应用的重要资源；然而，这些模型仍面临生成不准确信息或幻觉等问题。检索增强生成技术为模型更新知识、提升性能提供了解决方案。区别于以往采用专用交叉注意力机制帮助LLM编码检索文本的检索增强语言模型，BiomedRAG采用更简洁的方法，直接将基于分块的检索文档输入LLM。这种直接设计易于适配现有检索与语言模型，能有效绕过检索文档中的噪声信息，尤其在噪声密集型任务中表现突出。此外，我们展示了在生物医学领域利用LLM监督检索模型的潜力，使其能够检索到辅助语言模型提升预测质量的文档。实验表明，通过调优评分器，BiomedRAG在覆盖9个以上数据集的5项生物医学NLP任务（信息抽取（三元组抽取、关系抽取）、文本分类、链接预测与问答）中取得优越性能。例如，在三元组抽取任务中，BiomedRAG在GIT与ChemProt语料库上的微平均F1分数分别达到81.42和88.83，性能超越其他三元组抽取系统。