[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-31576":3,"doc-seo-31576":27},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"file_id":15,"file_url":16,"file_type":17,"file_size":18,"view_count":4,"is_deleted":4,"is_public":19,"is_downloadable":19,"audit_status":19,"page_count":20,"language":21,"language_code":22,"table_of_contents":23,"faqs":24,"seo_title":13,"seo_description":14,"update_tm":25,"read_time":26},31576,8796095462418,"Noah","https://ap-avatar.wpscdn.com/avatar/80000253c1241d02b47?x-image-process=image/resize,m_fixed,w_180,h_180&k=1778826106357471780",8,"Research & Report","Edge Based Collaborative Log Anomaly Detection Using Retrieval Augmented Language Models","Retrieval-Augmented Generation (RAG) improves Large Language Models by grounding inference in relevant retrieved examples, yet edge deployment is still insufficiently explored for system log anomaly detection. This work proposes an edge-based collaborative framework on NVIDIA Jetson Nano Orin Super, where neighbor nodes maintain local embedded log clusters and retrieve top-k similar cases for a target node. Aggregated neighbor responses are used to form LLM prompts, evaluated on OpenStack and BGL logs.","cbCaib5xZKrslsjW","https://ap.wps.com/l/cbCaib5xZKrslsjW","pdf",499567,1,7,"English","en","# Introduction\n## Motivation for edge-based analysis\n## LLM and RAG for anomaly detection\n# Proposed Collaborative Edge Framework\n## Local clustering and FAISS retrieval\n## Distributed query and response aggregation\n# Experimental Evaluation\n## Datasets and models\n## Accuracy results","[{\"question\":\"Which datasets and models are used for evaluation?\",\"answer\":\"Experiments use OpenStack and BGL logs from the LogHub benchmark repository, with quantized Granite3.2:8B, Granite3.3:8B, and Mistral:7B models hosted locally via OLLAMA.\"}]",1779742908,18,{"code":4,"msg":28,"data":29},"ok",{"site_id":30,"language":22,"slug":31,"title":13,"keywords":32,"description":14,"schema_data":33,"social_meta":76,"head_meta":78,"extra_data":80,"updated_unix":25},105,"edge-based-collaborative-log-anomaly-detection-using-retrieval-augmented-language-models","",{"@graph":34,"@context":75},[35,52,66],{"@type":36,"itemListElement":37},"BreadcrumbList",[38,42,46,49],{"item":39,"name":40,"@type":41,"position":19},"https://docshare.wps.com","Home","ListItem",{"item":43,"name":44,"@type":41,"position":45},"https://docshare.wps.com/document/","Document",2,{"item":47,"name":12,"@type":41,"position":48},"https://docshare.wps.com/document/research-report/",3,{"item":50,"name":13,"@type":41,"position":51},"https://docshare.wps.com/document/edge-based-collaborative-log-anomaly-detection-using-retrieval-augmented-language-models/31576/",4,{"url":50,"name":13,"@type":53,"author":54,"headline":13,"publisher":56,"fileFormat":59,"description":14,"dateModified":60,"datePublished":60,"encodingFormat":59,"isAccessibleForFree":61,"interactionStatistic":62},"DigitalDocument",{"name":9,"@type":55},"Person",{"url":39,"name":57,"@type":58},"DocShare","Organization","application/pdf","2026-05-25",true,{"@type":63,"interactionType":64,"userInteractionCount":4},"InteractionCounter",{"@type":65},"ViewAction",{"@type":67,"mainEntity":68},"FAQPage",[69],{"name":70,"@type":71,"acceptedAnswer":72},"Which datasets and models are used for evaluation?","Question",{"text":73,"@type":74},"Experiments use OpenStack and BGL logs from the LogHub benchmark repository, with quantized Granite3.2:8B, Granite3.3:8B, and Mistral:7B models hosted locally via OLLAMA.","Answer","https://schema.org",{"og:url":50,"og:type":77,"og:title":13,"og:site_name":57,"og:description":14},"article",{"robots":79,"canonical":50},"index,follow",{"doc_id":7,"site_id":30}]