Large language models (LLMs) are transforming the way information is retrieved with vast amounts of knowledge being summarized and presented via natural language conversations. Yet, LLMs are prone to highlight the most frequently seen pieces of information from the training set and to neglect the rare ones. In the field of biomedical research, latest discoveries are key to academic and industrial actors and are obscured by the abundance of an ever-increasing literature corpus (the information overload problem). Surfacing new associations between biomedical entities, e.g., drugs, genes, diseases, with LLMs becomes a challenge of capturing the long-tail knowledge of the biomedical scientific production. To overcome this challenge, Retrieval Augmented Generation (RAG) has been proposed to alleviate some of the shortcomings of LLMs by augmenting the prompts with context retrieved from external datasets. RAG methods typically select the context via maximum similarity search over text embeddings. In this study, we show that RAG methods leave out a significant proportion of relevant information due to clusters of over-represented concepts in the biomedical literature. We introduce a novel information-retrieval method that leverages a knowledge graph to downsample these clusters and mitigate the information overload problem. Its retrieval performance is about twice better than embedding similarity alternatives on both precision and recall. Finally, we demonstrate that both embedding similarity and knowledge graph retrieval methods can be advantageously combined into a hybrid model that outperforms both, enabling potential improvements to biomedical question-answering models.
Understanding the Behaviors of Environment-aware Information Retrieval
Fudan University（复旦大学）；Alibaba DAMO Academy（阿里巴巴达摩院）；Chinese University of Hong Kong（香港中文大学）；Stanford University（斯坦福大学）；Shanghai University of Finance and Economics（上海财经大学）
Improving Few-shot and Zero-shot Entity Linking with Coarse-to-Fine Lexicon-based Retriever
Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））；Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies（广东省新型安全智能技术重点实验室）；Central South University（中南大学）
MedCPT: Contrastive Pre-trained Transformers with Large-scale PubMed Search Logs for Zero-shot Biomedical Information Retrieval
National Center for Biotechnology Information (NCBI)（国家生物技术信息中心）；National Library of Medicine (NLM)（国家医学图书馆）；National Institutes of Health (NIH)（国立卫生研究院）
MedCPT 利用 2.55 亿条 PubMed 点击日志进行对比预训练，首次实现生物医学零样本语义检索，并在六个 IR 任务上超越 GPT-3 规模基线模型。
Exploration of Augmentation Strategies in Multi-modal Retrieval-Augmented Generation for the Biomedical Domain: A Case Study Evaluating Question Answering in Glycobiology
University of Maribor, Faculty of Health Sciences（莫拉维亚大学健康科学学院）；University of Ljubljana, Medical Factory（卢布尔雅那大学医疗工厂）；Genos Ltd（基因公司）；Center for Smart Health, School of Nursing The Hong Kong Polytechnic University（智能健康中心护理学院香港理工大学）；University of Zagreb, Faculty of Pharmacy（扎格雷布大学药学院）；Usher Institute University of Edinburgh（埃德蒙顿大学usher研究所）
Distilling Closed-Source LLM's Knowledge for Locally Stable and Economic Biomedical Entity Linking
Computer Network Information Center, Chinese Academy of Sciences（中国科学院计算机网络信息中心）；University of Chinese Academy of Sciences（中国科学院大学）；Changsha Aier Eye Hospital（长沙爱尔眼科医院）；Portland State University（波特兰州立大学）
GLiNER-BioMed: A Suite of Efficient Models for Open Biomedical Named Entity Recognition
Department of Radiology and Medical Informatics, Faculty of Medicine, University of Geneva（日内瓦大学医学院放射学与医学信息学系）；Knowledgator Engineering（Knowledgator工程）
Query pipeline optimization for cancer patient question answering systems
School of Computing and Information Systems, University of Melbourne（墨尔本大学计算与信息系统学院）；Health Data Science and Biostatistics, University of Texas Southwestern Medical Center（德克萨斯西南医学中心健康数据科学与生物统计学）
PrLM: Learning Explicit Reasoning for Personalized RAG via Contrastive Reward Optimization
Gaoling School of Artificial Intelligence\ University of China Beijing China；School of Information Technology；Gaoling School of Artificial Intelligence\ University of China
Retrieval-Augmented Generation with Graphs (GraphRAG)
Michigan State University（密歇根州立大学）；University of Oregon（俄勒冈大学）；Pacific Northwest National Laboratory（太平洋西北国家实验室）；Adobe Research（奥多比研究院）；Hippocratic AI（希波克拉底人工智能公司）；Amazon（亚马逊公司）；Meta；Snap Inc.（斯纳普公司）；The Home Depot（家得宝公司）
Benchmarking Retrieval-Augmented Large Language Models in Biomedical NLP: Application, Robustness, and Self-Awareness
Division of Computational Health Sciences, Department of Surgery University of Minnesota（大学医学计算科学系，外科系）；Institute for Health Informatics University of Minnesota（健康信息学研究所，明尼苏达大学）；Department of Electrical and Computer Engineering University of Minnesota（电气与计算机工程系，明尼苏达大学）
Harnessing Collective Intelligence of LLMs for Robust Biomedical QA: A Multi-Model Approach
Department of Informatics；Kapodistrian University of Athens, Greece；Institute for Fundamental Biomedical Science, Biomedical Sciences Research Center "Alexander Fleming", Greece；Department of Informatics \& Telematics, School of Digital Technology, Harokopio University, Greece；Archimedes, Athena Research Center, Greece
Knowledge-Driven Agentic Scientific Corpus Distillation Framework for Biomedical Large Language Models Training
Computer Network Information Center, Chinese Academy of Sciences, Beijing, China（中国科学院计算机网络信息中心）；University of Chinese Academy of Sciences, Beijing, China（中国科学院大学）；Duke-NUS Medical School, National University of Singapore, Singapore（新加坡国立大学杜克-新加坡医学部）
