# EidosDoc: Implicit Structure Encoding for Cost-Effective Semi-Structured Document QA

arXiv: https://arxiv.org/abs/2609.27784 · HTML: https://mlsanity.com/paper/2609.27784/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 38 references that are in the map.
- First posted on arXiv 17 Aug 2026.

## Builds on (most cited first, 30 of 31)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking](https://mlsanity.com/paper/2204.08387/) (2022)
- [DocFormer: End-to-End Transformer for Document Understanding](https://mlsanity.com/paper/2106.11539/) (2021)
- [Evaluating Protein Transfer Learning with TAPE](https://mlsanity.com/paper/1906.08230/) (2019)
- [Unifying Vision, Text, and Layout for Universal Document Processing](https://mlsanity.com/paper/2212.02623/) (2022)
- [Document Understanding Dataset and Evaluation (DUDE)](https://mlsanity.com/paper/2305.08455/) (2023)
- [mPLUG-DocOwl2: High-resolution Compressing for OCR-free Multi-page Document Understanding](https://mlsanity.com/paper/2409.03420/) (2024)
- [Language Models Enable Simple Systems for Generating Structured Views of Heterogeneous Data Lakes](https://mlsanity.com/paper/2304.09433/) (2023)
- [M3DocRAG: Multi-modal Retrieval is What You Need for Multi-page Multi-document Understanding](https://mlsanity.com/paper/2411.04952/) (2024)
- [PDFTriage: Question Answering over Long, Structured Documents](https://mlsanity.com/paper/2309.08872/) (2023)
- [SV-RAG: LoRA-Contextualizing Adaptation of MLLMs for Long Document Understanding](https://mlsanity.com/paper/2411.01106/) (2024)
- [PaddleOCR-VL-1.6: Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Training](https://mlsanity.com/paper/2606.03264/) (2026)
- [MEBench: Benchmarking Large Language Models for Cross-Document Multi-Entity Question Answering](https://mlsanity.com/paper/2502.18993/) (2025)
- [Towards Accurate and Efficient Document Analytics with Large Language Models](https://mlsanity.com/paper/2405.04674/) (2024)
- [SRAG: Structured Retrieval-Augmented Generation for Multi-Entity Question Answering over Wikipedia Graph](https://mlsanity.com/paper/2503.01346/) (2025)
- [MHier-RAG: Multi-Modal RAG for Visual-Rich Document Question-Answering via Hierarchical and Multi-Granularity Reasoning](https://mlsanity.com/paper/2508.00579/) (2025)
- [QUEST: Query Optimization in Unstructured Document Analysis](https://mlsanity.com/paper/2507.06515/) (2025)
- [SuperRAG: Beyond RAG with Layout-Aware Graph Modeling](https://mlsanity.com/paper/2503.04790/) (2025)
- [Analyzing the Efficacy of an LLM-Only Approach for Image-based Document Question Answering](https://mlsanity.com/paper/2309.14389/) (2023)
- [LAD-RAG: Layout-aware Dynamic RAG for Visually-Rich Document Understanding](https://mlsanity.com/paper/2510.07233/) (2025)
- [Simplifying Data Integration: SLM-Driven Systems for Unified Semantic Queries Across Heterogeneous Databases](https://mlsanity.com/paper/2504.05634/) (2025)
- [SQUiD: Synthesizing Relational Databases from Unstructured Text](https://mlsanity.com/paper/2505.19025/) (2025)
- [AnnoRetrieve: Efficient Structured Retrieval for Unstructured Document Analysis](https://mlsanity.com/paper/2604.02690/) (2026)
- [NeuSym-RAG: Hybrid Neural Symbolic Retrieval with Multiview Structuring for PDF Question Answering](https://mlsanity.com/paper/2505.19754/) (2025)
- [LightKGG: Simple and Efficient Knowledge Graph Generation from Textual Data](https://mlsanity.com/paper/2510.23341/) (2025)
- [MoDora: Tree-Based Semi-Structured Document Analysis System](https://mlsanity.com/paper/2602.23061/) (2026)
- [DocSage: An Information Structuring Agent for Multi-Doc Multi-Entity Question Answering](https://mlsanity.com/paper/2603.11798/) (2026)
- [Monte Carlo Tree Search for Table-to-Multimodal Report Generation](https://mlsanity.com/paper/2608.04071/) (2026)

## Built on by (most cited first, 1 of 1)

- [Structured Composition of Verifiable Atomic Insights for Table-to-Report Generation](https://mlsanity.com/paper/2610.03525/) (2026)

## Abstract (arXiv)

Semi-structured documents are ubiquitous in scientific reports, financial statements, and technical manuals. Question answering over such documents requires simultaneous understanding of text, tables, charts, and complex hierarchical layouts. Existing methods either rely on repeatedly calling large language models for structure parsing and retrieval, leading to high cost and large latency, or they flatten the document and lose layout and hierarchy information, sacrificing answer accuracy. To address this, we propose EidosDoc, a novel system that achieves state-of-the-art accuracy with minimal computational expense. Our approach introduces three core innovations. (1) An Implicit Structure Encoder trained via contrastive learning and a structure consistency loss. This module jointly embeds hierarchical relationships, spatial positions, and textual content into a dense vector space, capturing document structure holistically without the need for manually defined and error-prone constructions. (2) A Hybrid Retrieval Pipeline that leverages BM25, layout fingerprints, and a lightweight cross-encoder to perform high-precision retrieval entirely without invoking an LLM, drastically reducing cost and latency. (3) A Dynamic Evidence Expansion mechanism that adaptively retrieves spatially adjacent and structurally related evidence, overcoming the evidence omission common in fixed-path retrieval methods. We evaluate EidosDoc on four benchmarks, and comprehensive evaluations show that EidosDoc achieves a new state-of-the-art accuracy on the four benchmarks. Crucially, it does so with a 50 times reduction in cost and 4 times lower latency compared to the previous state-of-the-art Method. These results demonstrate that EidosDoc establishes a new optimal trade-off among accuracy, cost, and speed, offering a practical and scalable path for accurate semi-structured document analysis.