[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-83720-en":3,"doc-seo-83720-105":30,"detail-sidebar-cat-0-en-105":83},{"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,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},83720,4398048949847,"Eliana","https://ap-avatar.wpscdn.com/avatar/400002536579ef2da7f?_k=1778318612642679267",8,"Research & Report","TRIAGE Trustworthy Retrieval Instrumentation And Graph Evaluation","Knowledge graphs that power Graph-based Retrieval-Augmented Generation (Graph-RAG) are increasingly built via LLM-driven extraction, making failures harder to attribute than when experts curate them. TRIAGE introduces a stage-aware instrumentation framework spanning extraction, KG construction, validation, and usage. It attaches independently interpretable trust and cost metrics to KG implementation, expert-validated KG quality, and KG usage, enabling a diagnostic chain that localizes the first broken condition and maps it to remedial levers.","arXiv :2607 .03447v 1 [ cs .IR] 3 Jul 2026  \nTRIAGE: Trustworthy Retrieval Instrumentation And Graph Evaluation  \nAxel TahmasebiMoradi, Lucas Schott, Martin Royer  \nIRT-SystemX  \n[a.tahmasebimoradi@irt-systemx.fr](a.tahmasebimoradi@irt-systemx.fr) , [lucas.schott@irt-systemx.fr](lucas.schott@irt-systemx.fr) , [martin.royer@irt-systemx.fr](martin.royer@irt-systemx.fr)  \nAbstract. Knowledge graphs (KGs) that underpin Graph-based RetrievalAugmented Generation (Graph-RAG) are increasingly built automatically by LLM-driven extraction rather than curated by experts. Proper evaluation would require instrumenting all pertinent stages: extraction, graph construction, and inference, coherently enough to localize failures, so that a failure at one stage is not discovered as a wrong answer atthe end. We introduce TRIAGE, a stage-aware instrumentation framework for automated, document-grounded graph-RAG that asks not only whether the underlying graph can be trusted but at what cost it can be queried. TRIAGE attaches stage-specific, independently interpretable metrics to three stages: the KG Implementation (triple confidence, source coverage, and schema and canonicalization checks), the KG Validation by expert (graph-level structural quality, with correctness and completeness computed only as offline calibration when a reference is available), and the KG Usage (retrieval coverage, faithfulness, and retrieval cost);  \nthe deployed metrics need no gold annotations, the gold-requiring ones serving only as offline calibration. At usage time these metrics form a diagnostic chain of necessary conditions whose first broken link localizes the failure, and the diagnosis maps to the stage levers that can remedy it: extraction, graph and schema, or retrieval. TRIAGE is a theoretical framework with a proof of concept and a reproducible evaluation protocol.  \nKeywords: Knowledge Graphs · Graph RAG · Trustworthiness · Trust Metrics · Knowledge Graph Evaluation · Automated Knowledge Graph Construction  \n1 Introduction  \nContext and motivation. Large language models (LLMs) have transformed information access by enabling fluent, query-driven generation over vast document collections. Yet their most persistent failure mode remains hallucination: the generation of plausible but unsupported statements [28,42] . Retrieval-Augmented Generation (RAG) was introduced precisely to mitigate this risk by grounding generation in externally retrieved evidence [35] . However, when retrieval  \n2 Axel TahmasebiMoradi, Lucas Schott, Martin Royer  \noperates over flat vector indexes, it recovers semantically similar passages without capturing the relational structure that multi-hop or entity-centric questions demand [13,9] . Knowledge graphs (KGs) offer a principled alternative: by representing factual knowledge as typed, directed triples (s,p, o) [23], they make relationships explicit and support structured, traceable reasoning paths. Graphbased RAG systems exploit this structure to improve retrieval precision and answer faithfulness [13,20,9] . Yet the KG itself is increasingly built automatically by LLM-driven pipelines rather than curated by experts, introducing a new layer of uncertainty, even as we continue to judge such systems only by whether the final answer looks right. The central question of this paper is therefore twofold: when and how much we can trust the graph that underpins retrieval, and at what cost, in pathfinding time, retrieval latency, and compute, it can be queried. A graph that is trustworthy but too costly to traverse is no more deployable than one that is cheap but wrong, so an end-to-end account of graph-RAG quality must speak to both.  \nThe gap we are filling. Recent work on trustworthy KG engineering, in particular the TKG methodology [2], provides a rigorous lifecycle framework covering construction, validation, deployment, and governance of KGs in safetycritical settings, and defines formal effectiveness metrics for correctness, completeness, a","cbCais9pA7TDHGOM","https://ap.wps.com/l/cbCais9pA7TDHGOM","pdf",714955,2,1,49,"English","en",105,"# Introduction\n## Context and motivation\n## The gap we are filling\n## Contributions","[{\"question\":\"How does TRIAGE diagnose failures and suggest remedies?\",\"answer\":\"It uses a diagnostic chain of necessary conditions so that the first broken link identifies the failing stage, then maps that diagnosis to stage levers such as extraction, graph/schema fixes, or retrieval adjustments.\"}]",1784189967,123,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":78,"head_meta":80,"extra_data":82,"updated_unix":28},"triage-trustworthy-retrieval-instrumentation-and-graph-evaluation","",{"@graph":36,"@context":77},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,47,50],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":20},"https://docshare.wps.com/document/","Document",{"item":48,"name":12,"@type":43,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/triage-trustworthy-retrieval-instrumentation-and-graph-evaluation/83720/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-27","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71],{"name":72,"@type":73,"acceptedAnswer":74},"How does TRIAGE diagnose failures and suggest remedies?","Question",{"text":75,"@type":76},"It uses a diagnostic chain of necessary conditions so that the first broken link identifies the failing stage, then maps that diagnosis to stage levers such as extraction, graph/schema fixes, or retrieval adjustments.","Answer","https://schema.org",{"og:url":51,"og:type":79,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":81,"canonical":51},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":84},[85,89,93,97,102,107,112,115,120,123,127],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":86,"show_sort_weight":87,"slug":88},"Story & Novel",90,"story-novel",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":90,"show_sort_weight":91,"slug":92},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Exam",70,"exam",{"id":98,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},5,"Comic",60,"comic",{"id":103,"doc_module":4,"doc_module_name":46,"category_name":104,"show_sort_weight":105,"slug":106},6,"Technology",50,"technology",{"id":108,"doc_module":4,"doc_module_name":46,"category_name":109,"show_sort_weight":110,"slug":111},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":113,"slug":114},30,"research-report",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},9,"Religion & Spirituality",20,"religion-spirituality",{"id":118,"doc_module":4,"doc_module_name":46,"category_name":121,"show_sort_weight":118,"slug":122},"World Cup","world-cup",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":124,"slug":126},10,"Lifestyle","lifestyle",{"id":128,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":98,"slug":130},19,"General","general"]