ENTLORE: A Graph-Grounded Benchmark for Latent Organizational Reasoning in Enterprise Question Answering

• URL: http://arxiv.org/abs/2608.10679v2
• Date: Wed, 12 Aug 2026 10:20:02 GMT
• Title: ENTLORE: A Graph-Grounded Benchmark for Latent Organizational Reasoning in Enterprise Question Answering
• Abstract summary: We introduce ENTLORE, a graph-grounded benchmark construction framework that reconstructs an audited enterprise world from routine documents.<n>Versioned organizational conventions certify derived relations in a truth graph, enabling complete golden answers and proof certificates.<n> ENTLORE contains 2,341 documents from three source types and 907 questions spanning explicit lookup, cross-source composition, and latent organizational reasoning.
• Score: 42.15843879644805
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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. 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 https://github.com/scitix/entlore .

Related papers

• VisDocAgentBench: Benchmarking Agents for Visually Rich Document Retrieval [65.89247522243959]
  VisDocAgentBench is a closed-corpus benchmark comparing static and agentic retrieval under a ranked-output contract.<n>It contains 2,375 pages from 100 documents and 120 unique-target queries balanced across direct, one-bridge, and two-bridge evidence structures.<n>A strong late-interaction visual retriever reaches 97.50% Recall@1 on direct items but 2.50% on two-bridge items, exposing the limits of query--target matching when relevance depends on corpus context.
  arXiv  Detail & Related papers  (2026-08-18T15:23:06Z)
• Beyond Tables: Doc2DB-Bench for Relationally Faithful Document-to-Database Construction [4.062546658033461]
  We introduce Doc2DB-Bench, a benchmark for Document-to-Database construction.<n>It contains 203 long-document instances across 42 schemas and seven domain groups, with 117 entity tables, 132 relationship tables, 7,341 rows, and 41,935 cells.
  arXiv  Detail & Related papers  (2026-08-09T03:58:39Z)
• DocTrace: Towards Traceable Long Document VQA via Hierarchical Evidence Graph Reasoning [14.841209914774778]
  Long Document Visual Question Answering (LongDocVQA) requires Multimodal Large Language Models (MLLMs) to locate, integrate, and reason over heterogeneous document elements distributed across multiple pages.<n>Existing approaches, including end-to-end MLLMs, often lack explicit mechanisms to represent and verify how grounded evidence is progressively composed during reasoning.<n>We propose DocTrace, a hierarchical framework that progressively performs evidence localization, structured document parsing, and evidence graph reasoning.
  arXiv  Detail & Related papers  (2026-08-04T08:04:59Z)
• Beyond Triplet Plausibility: Relation Set Completion in Knowledge Graphs [48.16012222834734]
  We introduce a relation set completion task (RSC) and a relation set Embedding model (RelSetE)<n>RSC aims to reason about missing relations that are semantically compatible with a given entity.<n>RelSetE models latent patterns among the observed relations of entities to infer missing ones.
  arXiv  Detail & Related papers  (2026-06-29T06:54:40Z)
• Trace Only What You Need: Structure-Aware On-Demand Hypergraph Memory for Long-Document Question Answering [11.17007249581283]
  Long-document question answering requires large language models to reason over evidence scattered across lengthy documents.<n>Existing structured RAG methods face three limitations: costly query-agnostic knowledge organization, insufficient use of original document structure, and no reuse of historical reasoning experience.<n>We propose DocTrace, a multi-agent RAG framework for long-document QA that supports query-triggered knowledge organization, document-structure-aware and experience-guided reasoning.
  arXiv  Detail & Related papers  (2026-06-09T14:29:06Z)
• DocSync: Agentic Documentation Maintenance via Critic-Guided Reflexion [0.0]
  DocSync is an agentic workflow that frames documentation maintenance as a structurally grounded, iterative generation task.<n>We empirically evaluate a resource-constrained implementation of DocSync-using a LoRA-adapted small language model.<n>Our findings demonstrate that this AST-aware agentic approach substantially outperforms standard encoder-decoder baselines.
  arXiv  Detail & Related papers  (2026-05-04T02:41:33Z)
• BookRAG: A Hierarchical Structure-aware Index-based Approach for Retrieval-Augmented Generation on Complex Documents [11.158307125677375]
  Retrieval-Augmented Generation (RAG) queries highly relevant information from external complex documents.<n>We introduce BookRAG, a novel RAG approach targeted for documents with a hierarchical structure.<n>BookRAG achieves state-of-the-art performance, significantly outperforming baselines in both retrieval recall and QA accuracy.
  arXiv  Detail & Related papers  (2025-12-03T03:40:49Z)
• Hierarchical Retrieval with Evidence Curation for Open-Domain Financial Question Answering on Standardized Documents [9.173952465423966]
  standardized documents share similar formats such as repetitive boilerplate texts, and similar table structures.<n>This similarity forces traditional RAG methods to misidentify near-duplicate text, leading to duplicate retrieval that undermines accuracy and completeness.<n>We propose the Hierarchical Retrieval with Evidence Curation framework to address these issues.
  arXiv  Detail & Related papers  (2025-05-26T11:08:23Z)
• Unstructured Evidence Attribution for Long Context Query Focused Summarization [53.08341620504465]
  We propose to extract unstructured (i.e., spans of any length) evidence in order to acquire more relevant and consistent evidence than in the fixed granularity case.<n>We show how existing systems struggle to copy and properly cite unstructured evidence, which also tends to be "lost-in-the-middle"
  arXiv  Detail & Related papers  (2025-02-20T09:57:42Z)
• Knowledge-Aware Query Expansion with Large Language Models for Textual and Relational Retrieval [49.42043077545341]
  We propose a knowledge-aware query expansion framework, augmenting LLMs with structured document relations from knowledge graph (KG)<n>We leverage document texts as rich KG node representations and use document-based relation filtering for our Knowledge-Aware Retrieval (KAR)
  arXiv  Detail & Related papers  (2024-10-17T17:03:23Z)
• PDFTriage: Question Answering over Long, Structured Documents [60.96667912964659]
  Representing structured documents as plain text is incongruous with the user's mental model of these documents with rich structure. We propose PDFTriage that enables models to retrieve the context based on either structure or content. Our benchmark dataset consists of 900+ human-generated questions over 80 structured documents.
  arXiv  Detail & Related papers  (2023-09-16T04:29:05Z)
• GERE: Generative Evidence Retrieval for Fact Verification [57.78768817972026]
  We propose GERE, the first system that retrieves evidences in a generative fashion. The experimental results on the FEVER dataset show that GERE achieves significant improvements over the state-of-the-art baselines.
  arXiv  Detail & Related papers  (2022-04-12T03:49:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.