a benchmark framework that evaluates enterprise question answering by requiring recovery of implicit organizational relations across routine documents, revealing that even with gold sources many latent reasoning questions remain unanswered.</p>\n","updatedAt":"2026-08-18T02:57:22.450Z","author":{"_id":"6a7bd3fdc8085348a10798b3","avatarUrl":"/avatars/104ef9a98a7f939ceea538c43ae9cbc8.svg","fullname":"Akrin Zheng","name":"Akrin-scitix","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":1,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.9331690073013306},"editors":["Akrin-scitix"],"editorAvatarUrls":["/avatars/104ef9a98a7f939ceea538c43ae9cbc8.svg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2608.10679","authors":[{"_id":"6a7bd4341653ef87c6af1bc9","user":{"_id":"6a7bd3fdc8085348a10798b3","avatarUrl":"/avatars/104ef9a98a7f939ceea538c43ae9cbc8.svg","isPro":false,"fullname":"Akrin Zheng","user":"Akrin-scitix","type":"user","name":"Akrin-scitix"},"name":"Akrin Zheng","status":"claimed_verified","statusLastChangedAt":"2026-08-12T08:45:05.061Z","hidden":false},{"_id":"6a7bd4341653ef87c6af1bca","name":"Alexander Wu","hidden":false},{"_id":"6a7bd4341653ef87c6af1bcb","name":"Alaia Liu","hidden":false}],"publishedAt":"2026-08-11T00:00:00.000Z","submittedOnDailyAt":"2026-08-18T00:00:00.000Z","title":"ENTLORE: A Graph-Grounded Benchmark for Latent Organizational Reasoning in Enterprise Question Answering","submittedOnDailyBy":{"_id":"6a7bd3fdc8085348a10798b3","avatarUrl":"/avatars/104ef9a98a7f939ceea538c43ae9cbc8.svg","isPro":false,"fullname":"Akrin Zheng","user":"Akrin-scitix","type":"user","name":"Akrin-scitix"},"summary":"Enterprise question answering is framed as retrieving internal documents and generating grounded answers. Routine enterprise records, however, are work by-products in which required organizational relations remain implicit across heterogeneous sources. Existing benchmarks provide realistic multi-source evidence, but often materialize a predefined answer path and therefore test the composition of stated facts rather than recovery of a target relation absent from the corpus. We call the latter capability latent organizational reasoning.\n We introduce ENTLORE, a graph-grounded benchmark construction framework that reconstructs an audited enterprise world from routine documents, authoritative organizational tables, and operational records. Versioned organizational conventions certify derived relations in a truth graph, enabling complete golden answers and proof certificates. The aligned anonymized release exposes only the document corpus while withholding private structure and target relations. ENTLORE contains 2,341 documents from three source types and 907 questions spanning explicit lookup, cross-source composition, and latent organizational reasoning, evaluated across 56 model and access configurations. Structuring the released world as an induced entity graph or navigable knowledge base gives the strongest deployable results. Yet supplying gold documents still leaves 30.4% of latent questions unanswered, versus 12.6% and 6.2% for explicit and compositional questions. Enterprise QA therefore depends not only on document recall, but also on whether implicit organizational relations become usable. The benchmark, data, and code are publicly available at ENTLORE.","upvotes":3,"discussionId":"6a7bd4341653ef87c6af1bcc","githubRepo":"https://github.com/scitix/entlore","githubRepoAddedBy":"user","ai_summary":"ENTLORE is a benchmark framework that evaluates enterprise question answering by requiring recovery of implicit organizational relations across routine documents, revealing that even with gold sources many latent reasoning questions remain unanswered.","ai_keywords":["graph-grounded benchmark","induced entity graph","navigable knowledge base","latent organizational reasoning","cross-source composition"],"ai_summary_model":"thinkingmachines/Inkling-Small","githubStars":2,"organization":{"_id":"693b8e268c81b3c6b2b87880","name":"ScitiX1","fullname":"Scitix (SGP) Tech PTE. LTD.","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/693b8c74ca53da32fcf25036/uT7jvw7T0nW-nDJ1FcQ0U.png"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"6a7bd3fdc8085348a10798b3","avatarUrl":"/avatars/104ef9a98a7f939ceea538c43ae9cbc8.svg","isPro":false,"fullname":"Akrin Zheng","user":"Akrin-scitix","type":"user"},{"_id":"63ac5701c21e60a3e9b58aa7","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/63ac5701c21e60a3e9b58aa7/g6EX7diOpuA94R2ab-rZC.png","isPro":true,"fullname":"Dipankar Sarkar","user":"dipankarsarkar","type":"user"},{"_id":"68e4ba9bb3738c567535654e","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/68e4ba9bb3738c567535654e/DmkMgEaKb3N3bnbJYk1cC.png","isPro":false,"fullname":"wu","user":"realty2333","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"organization":{"_id":"693b8e268c81b3c6b2b87880","name":"ScitiX1","fullname":"Scitix (SGP) Tech PTE. LTD.","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/693b8c74ca53da32fcf25036/uT7jvw7T0nW-nDJ1FcQ0U.png"},"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2608/2608.10679.md","query":{}}">

Get this paper in your agent:

Don't have the latest CLI?

Cite arxiv.org/abs/2608.10679 in a model README.md to link it from this page.

Cite arxiv.org/abs/2608.10679 in a Space README.md to link it from this page.

Add this paper to a collection to link it from this page.