Document QA

QA: Question Answering

Follow this topic Ask about this topic

Document question answering studies how models find and combine evidence in sources such as PDFs, reports, forms, and document collections. Common approaches include retrieval-augmented generation, layout-aware and multimodal models, hierarchical indexes, and agents that navigate pages or inspect selected regions. Benchmarks increasingly test long-context and multi-document reasoning, numerical and temporal questions, and whether answers are supported by precise citations or visual evidence. Models still struggle to gather dispersed evidence and interpret complex layouts, while systems trade accuracy against latency, cost, and reliability.

Latest papers

93 papers12 papers in the last four weeks, up 50% on the four weeks before. 0.1% of all new papers.

May 29, 2026

Office Comprehension Benchmark

We introduce Office Comprehension Bench (OCB), the first public benchmark to jointly evaluate LLM systems on Word, Excel, and PowerPoint comprehension over native file formats (.docx, .xlsx, .pptx) and their variants. OCB consists of two tracks. File Fidelity Q&A tests structural and visual perception of office artifacts - tables, charts, embedded images, formulas, and app-specific elements such as headers, speaker notes, and named ranges. Domain Q&A tests expert-level reasoning grounded in real-world industry documents across 12 professional domains, with queries requiring multi-step analysis and synthesis across documents. Each reference answer is decomposed into atomic, binary-gradable claims, and an ensemble of LLM judges scores responses against each claim independently. Even the strongest frontier system in its default reasoning mode reaches only about 59.3% on Domain Q&A; increasing thinking depth within a tier does not move performance materially, while moving to a higher product tier yields modest gains. We release the dataset, evaluation tooling, judge prompt, and a public leaderboard.

Firoz Shaik, Mateus Picanço Lima Gomes, Tanvir Aumi +17

Microsoft · † Work done while at Microsoft.

Document Understanding LLM Evaluation Document QA Knowledge-Intensive QA

May 28, 2026

HiKEY: Hierarchical Multimodal Retrieval for Open-Domain Document Question Answering

Retrieval-augmented generation (RAG) for document-based Open-domain Question Answering (ODQA) on large-scale industrial corpora faces two critical bottlenecks: routing failure in locating the correct document and evidence fragmentation in integrating scattered information. Existing approaches relying on flat text chunks or page-level images inherently struggle to (i) precisely pinpoint the target document among thousands of candidates and (ii) organically connect multimodal evidence, such as tables and figures, within a limited token budget. To address these challenges, we propose HiKEY, a hierarchical tree-based multimodal retrieval framework that elevates document hierarchy to a first-class retrieval signal. Instead of simple chunking, HiKEY reconstructs a logical heterogeneous graph via Document Hierarchical Parsing (DHP), explicitly encoding parent-child relationships. Adopting a hierarchical coarse-to-fine strategy, the framework (1) performs global routing to rapidly prune the search space using hierarchical indexing, and (2) conducts fine-grained retrieval to rank sections by employing a multimodal fusion strategy that captures the most discriminative evidence. Finally, HiKEY assembles a token-efficient evidence subgraph via a hybrid structural-semantic packing strategy. Experiments on ODQA benchmarks demonstrate that HiKEY significantly outperforms page- and chunk-based baselines, improving retrieval recall by up to 12.9% and end-to-end QA performance by up to 6.8%.

Joongmin Shin, Gyuho Shim, Jeongbae Park +2

Human-inspired AI Research, Korea University · Department of Computer Science and Engineering, Korea University · Computer Science and Engineering, Konkuk University

Multimodal RAG Multimodal IR Graph Retrieval-Augmented Generation Document QA

May 20, 2026

ACL-Verbatim: hallucination-free question answering for research

Academic researchers need efficient and reliable methods for collecting high-quality information from trusted sources, but modern tools for AI-assisted research still suffer from the tendency of Large Language Models (LLMs) to produce factually inaccurate or nonsensical output, commonly referred to as hallucinations. We apply the extractive question answering system VerbatimRAG to research papers in the ACL Anthology, directly mapping user queries to verbatim text spans in retrieved documents. We contribute a novel ground truth dataset for the task of mapping user queries to relevant text spans in research papers, and use it to train and evaluate a variety of extractive models. Human annotation is performed by NLP researchers and is based on synthetic user queries generated using a custom pipeline based on the ScIRGen methodology, paired with chunks of research papers retrieved by VerbatimRAG. On this benchmark, a 150M-parameter ModernBERT token classifier trained on silver supervision from our pipeline achieves the best word-level F1 (53.6), ahead of the strongest evaluated LLM extractor (48.7).

Gábor Recski, Szilveszter Tóth, Nadia Verdha +2

TU Wien · KR Labs

Hallucination in Language Models Retrieval-Augmented Generation LLM Hallucination Mitigation Question Answering Document QA Factual QA+1

May 13, 2026

CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligence

Multimodal Large Language Models (MLLMs) have significantly advanced document understanding, yet current Doc-VQA evaluations score only the final answer and leave the supporting evidence unchecked. This answer-only approach masks a critical failure mode: a model can land on the correct answer while grounding it in the wrong passage---a critical risk in high-stakes domains like law, finance, and medicine, where every conclusion must be traceable to a specific source region. To address this, we introduce CiteVQA, a benchmark that requires models to return element-level bounding-box citations alongside each answer, evaluating both jointly. CiteVQA comprises 1,897 questions across 711 PDFs spanning seven domains and two languages, averaging 40.6 pages per document. To ensure fidelity and scalability, the ground-truth citations are generated by an automated pipeline---which identifies crucial evidence via masking ablation and enforces multi-stage quality control. At the core of our evaluation is Strict Attributed Accuracy (SAA), which credits a prediction only when the answer and the cited region are both correct. Auditing 20 MLLMs reveals a pervasive Attribution Hallucination: models frequently produce the right answer while citing the wrong region. The strongest system (Gemini-3.1-Pro-Preview) achieves an SAA of only 76.0, and the strongest open-source MLLM reaches just 22.5. Ultimately, towards trustworthy document intelligence, CiteVQA exposes a reliability gap that answer-only evaluations overlook, providing the instrumentation needed to close it. Our repository is available at https://github.com/opendatalab/CiteVQA.

Dongsheng Ma, Jiayu Li, Zhengren Wang +9

Peking University · Shanghai Artificial Intelligence Laboratory

VLM Evaluation Citation Verification Document QA Citation Hallucination Evidence-Grounded QA

May 11, 2026

Qwen Goes Brrr: Off-the-Shelf RAG for Ukrainian Multi-Domain Document Understanding

We participated in the Fifth UNLP shared task on multi-domain document understanding, where systems must answer Ukrainian multiple-choice questions from PDF collections and localize the supporting document and page. We propose a retrieval-augmented pipeline built around three ideas: contextual chunking of PDFs, question-aware dense retrieval and reranking conditioned on both the question and answer options, and constrained answer generation from a small set of reranked passages. Our final system uses Qwen3-Embedding-8B for retrieval, a fine-tuned Qwen3-Reranker-8B for passage ranking, and Qwen3-32B for answer selection. On a held-out split, reranking improves Recall@1 from 0.6957 to 0.7935, while using the top-2 reranked passages raises answer accuracy from 0.9348 to 0.9674. Our best leaderboard run reached 0.9452 on the public leaderboard and 0.9598 on the private leaderboard. Our results suggest that, under strict code-competition constraints, preserving document structure and making relevance estimation aware of the answer space are more effective than adding complex downstream heuristics.

Anton Bazdyrev, Ivan Bashtovyi, Ivan Havlytskyi +2

National Technical University of Ukraine "Igor Sikorsky Kyiv Polytechnic Institute"

Retrieval-Augmented Generation LLM Reranking Document QA Multilingual QA Multi-Document QA

May 11, 2026

ASTRA-QA: A Benchmark for Abstract Question Answering over Documents

Document-based question answering (QA) increasingly includes abstract questions that require synthesizing scattered information from long documents or across multiple documents into coherent answers. However, this setting is still poorly supported by existing benchmarks and evaluation methods, which often lack stable abstract references or rely on coarse similarity metrics and unstable head-to-head comparisons. To alleviate this issue, we introduce ASTRA-QA, a benchmark for AbSTRAct Question Answering over documents. ASTRA-QA contains 869 QA instances over academic papers and news documents, covering five abstract question types and three controlled retrieval scopes. Each instance is equipped with explicit evaluation annotations, including answer topic sets, curated unsupported topics, and aligned evidence. Building on these annotations, ASTRA-QA assesses whether answers cover required key points and avoid unsupported content by directly scoring topic coverage and curated unsupported content, enabling scalable evaluation without exhaustive head-to-head comparisons. Experiments with representative Retrieval-Augmented Generation (RAG) methods spanning vanilla, graph-based, and hierarchical retrieval settings show that ASTRA-QA provides reference-grounded diagnostics for coverage, hallucination, and retrieval-scope robustness. Our dataset and code are available at https://xinyangsally.github.io/astra-benchmark.

Shu Wang, Shansong Zhou, Xinyang Wang +3

The Chinese University of Hong Kong, Shenzhen · Data Science Group, Huolala

Question Answering Document QA RAG Evaluation

May 9, 2026

DocScope: Benchmarking Verifiable Reasoning for Trustworthy Long-Document Understanding

Evaluating whether Multimodal Large Language Models can produce trustworthy, verifiable reasoning over long, visually rich documents requires evaluation beyond end-to-end answer accuracy. We introduce DocScope, a benchmark that formulates long-document QA as a structured reasoning trajectory prediction problem: given a complete PDF document and a question, the model outputs evidence pages, supporting evidence regions, relevant factual statements, and a final answer. We design a four-stage evaluation protocol -- Page Localization, Region Grounding, Fact Extraction, and Answer Verification -- that audits each level of the trajectory independently through inter-stage decoupling, with all judges selected and calibrated via human alignment studies. DocScope comprises 1,124 questions derived from 273 documents, with all hierarchical evidence annotations completed by human annotators. We benchmark 6 proprietary models, 12 open-weight models, and several domain-specific systems. Our experiments reveal that answer accuracy cannot substitute for trajectory-level evaluation: even among correct answers, the highest observed rate of complete evidence chains is only 29%. Across all models, region grounding remains the weakest trajectory stage. Furthermore, the primary difficulty stems from aggregating evidence dispersed across long distances and multiple document clusters, while an oracle study identifies faithful perception and fact extraction as the dominant capability bottleneck. Cross-architecture comparisons further suggest that activated parameter count matters more than total scale. The benchmark and code will be publicly released at https://github.com/MiliLab/DocScope.

Xiang Feng, Jiawei Zhou, Zhangfeng Huang +6

School of Computer Science, National Engineering Research Center for Multimedia Software and Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University, China · Alibaba Group, Hangzhou, China · Independent Researcher +1

Multimodal Understanding LLM Answer Verification LLM Grounding Multimodal QA LLM Reliability Document QA+2

May 7, 2026

Towards Self-Explainable Document Visual Question Answering with Chain-of-Explanation Predictions

Document Visual Question Answering (DocVQA) requires vision-language models to reason not only about what information in a document is relevant to a question, but also where the answer is grounded on the page. Existing DocVQA models entangle question-relevant evidence and answer localization and operate largely as black boxes, offering limited means to verify how predictions depend on visual evidence. We propose CoExVQA, a self-explainable DocVQA framework with a grounded reasoning process through a chain-of-explanation design. CoExVQA first identifies question-relevant evidence, then explicitly localizes the answer region, and finally decodes the answer exclusively from the grounded region. Prediction via CoExVQA's chain-of-explanation enables direct inspection and verification of the reasoning process across modalities. Empirical results show that restricting decoding to grounded evidence achieves SotA explainable DocVQA performance on PFL-DocVQA, improving ANLS by 12% over the current explainable baselines while providing transparent and verifiable predictions.

Kjetil Indrehus, Adrian Duric, Changkyu Choi +1

Department of Informatics, University of Oslo · Integreat – Norwegian Centre for Knowledge-driven Machine Learning · TRUST – The Norwegian Centre for Trustworthy AI

Vision-Language Grounding Document QA

Apr 24, 2026

DocPrune:Efficient Document Question Answering via Background, Question, and Comprehension-aware Token Pruning

Recent advances in vision-language models have demonstrated remarkable performance across diverse multi-modal tasks, including document question answering that leverages structured visual cues from text, tables, and figures. However, unlike natural images, document images contain large backgrounds and only sparse supporting evidence, leading to the inefficient consumption of substantial computational resources, especially for long documents. We observe that existing token-reduction methods for natural images and videos fall short in utilizing the structural sparsity unique to documents. To address this, we propose DocPrune, a training-free and progressive document token pruning framework designed for efficient long-document understanding. The proposed method preserves only the essential tokens for the task while removing unnecessary ones, such as background or question-irrelevant tokens. Moreover, it automatically selects the appropriate layers to initiate token pruning based on the model's level of comprehension. Our experiments on the M3DocRAG show that DocPrune improves throughput by 3.0x and 3.3x in the encoder and decoder, respectively, while boosting the F1 score by +1.0, achieving both higher accuracy and efficiency without any additional training.

Joonmyung Choi, Sanghyeok Lee, Jongha Kim +4

Korea University · KAIST · Adobe Research

Efficient VLM Inference Document QA Multimodal Token Compression Visual Token Pruning Document Image Understanding

Apr 24, 2026

Navigating Large-Scale Document Collections: MuDABench for Multi-Document Analytical QA

This paper introduces the task of analytical question answering over large, semi-structured document collections. We present MuDABench, a benchmark for multi-document analytical QA, where questions require extracting and synthesizing information across numerous documents to perform quantitative analysis. Unlike existing multi-document QA benchmarks that typically require information from only a few documents with limited cross-document reasoning, MuDABench demands extensive inter-document analysis and aggregation. Constructed via distant supervision by leveraging document-level metadata and annotated financial databases, MuDABench comprises over 80,000 pages and 332 analytical QA instances. We also propose an evaluation protocol that measures final answer accuracy and uses intermediate-fact coverage as an auxiliary diagnostic signal for the reasoning process. Experiments reveal that standard RAG systems, which treat all documents as a flat retrieval pool, perform poorly. To address these limitations, we propose a multi-agent workflow that orchestrates planning, extraction, and code generation modules. While this approach substantially improves both process and outcome metrics, a significant gap remains compared to human expert performance. Our analysis identifies two primary bottlenecks: single-document information extraction accuracy and insufficient domain-specific knowledge in current systems. MuDABench is available at https://github.com/Zhanli-Li/MuDABench.

Zhanli Li, Yixuan Cao, Lvzhou Luo +1

State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences (CAS), Beijing 100190, China · University of Chinese Academy of Sciences, Beijing 100049, China

Multi-Document QA Document QA RAG Evaluation

Apr 21, 2026

An Answer is just the Start: Related Insight Generation for Open-Ended Document-Grounded QA

Answering open-ended questions remains challenging for AI systems because it requires synthesis, judgment, and exploration beyond factual retrieval, and users often refine answers through multiple iterations rather than accepting a single response. Existing QA benchmarks do not explicitly support this refinement process. To address this gap, we introduce a new task, document-grounded related insight generation, where the goal is to generate additional insights from a document collection that help improve, extend, or rethink an initial answer to an open-ended question, ultimately supporting richer user interaction and a better overall question answering experience. We curate and release SCOpE-QA (Scientific Collections for Open-Ended QA), a dataset of 3,000 open-ended questions across 20 research collections. We present InsightGen, a two-stage approach that first constructs a thematic representation of the document collection using clustering, and then selects related context based on neighborhood selection from the thematic graph to generate diverse and relevant insights using LLMs. Extensive evaluation on 3,000 questions using two generation models and two evaluation settings shows that InsightGen consistently produces useful, relevant, and actionable insights, establishing a strong baseline for this new task.

Saransh Sharma, Pritika Ramu, Aparna Garimella +1

Adobe Research, India · University of Maryland, College Park

Scientific QA Document QA

Apr 16, 2026

Toward Agentic RAG for Ukrainian

We present an initial investigation into Agentic Retrieval-Augmented Generation (RAG) for Ukrainian, conducted within the UNLP 2026 Shared Task on Multi-Domain Document Understanding. Our system combines two-stage retrieval (BGE-M3 with BGE reranking) with a lightweight agentic layer performing query rephrasing and answer-retry loops on top of Qwen2.5-3B-Instruct. Our analysis reveals that retrieval quality is the primary bottleneck: agentic retry mechanisms improve answer accuracy but the overall score remains constrained by document and page identification. We discuss practical limitations of offline agentic pipelines and outline directions for combining stronger retrieval with more advanced agentic reasoning for Ukrainian.

Marta Sumyk, Oleksandr Kosovan

Ukrainian Catholic University, Lviv, Ukraine

Agentic RAG Document QA

Apr 15, 2026

Doc-V*:Coarse-to-Fine Interactive Visual Reasoning for Multi-Page Document VQA

Multi-page Document Visual Question Answering requires reasoning over semantics, layouts, and visual elements in long, visually dense documents. Existing OCR-free methods face a trade-off between capacity and precision: end-to-end models scale poorly with document length, while visual retrieval-based pipelines are brittle and passive. We propose Doc-

V^*

, an OCR-free agentic framework that casts multi-page DocVQA as sequential evidence aggregation. Doc-

V^*

begins with a thumbnail overview, then actively navigates via semantic retrieval and targeted page fetching, and aggregates evidence in a structured working memory for grounded reasoning. Trained by imitation learning from expert trajectories and further optimized with Group Relative Policy Optimization, Doc-

V^*

balances answer accuracy with evidence-seeking efficiency. Across five benchmarks, Doc-

V^*

outperforms open-source baselines and approaches proprietary models, improving out-of-domain performance by up to 47.9% over RAG baseline. Other results reveal effective evidence aggregation with selective attention, not increased input pages.

Yuanlei Zheng, Pei Fu, Hang Li +9

School of Software Engineering, Huazhong University of Science and Technology · MiLM Plus, Xiaomi Inc. · School of Computer Science and Technology, Huazhong University of Science and Technology +1

Document QA Long-Document VQA VLM Reasoning

Apr 14, 2026

NaviRAG: Towards Active Knowledge Navigation for Retrieval-Augmented Generation

Retrieval-augmented generation (RAG) typically relies on a flat retrieval paradigm that maps queries directly to static, isolated text segments. This approach struggles with more complex tasks that require the conditional retrieval and dynamic synthesis of information across different levels of granularity (e.g., from broad concepts to specific evidence). To bridge this gap, we introduce NaviRAG, a novel framework that shifts from passive segment retrieval to active knowledge navigation. NaviRAG first structures the knowledge documents into a hierarchical form, preserving semantic relationships from coarse-grained topics to fine-grained details. Leveraging this reorganized knowledge records, a large language model (LLM) agent actively navigates the records, iteratively identifying information gaps and retrieving relevant content from the most appropriate granularity level. Extensive experiments on long-document QA benchmarks show that NaviRAG consistently improves both retrieval recall and end-to-end answer performance over conventional RAG baselines. Ablation studies confirm performance gains stem from our method's capacity for multi-granular evidence localization and dynamic retrieval planning. We further discuss efficiency, applicable scenario, and future directions of our method, hoping to make RAG systems more intelligent and autonomous.

Jihao Dai, Dingjun Wu, Yuxuan Chen +4

Tsinghua University · Nanjing University · Northeastern University

Retrieval-Augmented Generation Agentic RAG Information Retrieval Document QA

Apr 10, 2026

VISOR: Agentic Visual Retrieval-Augmented Generation via Iterative Search and Over-horizon Reasoning

Visual Retrieval-Augmented Generation (VRAG) empowers Vision-Language Models to retrieve and reason over visually rich documents. To tackle complex queries requiring multi-step reasoning, agentic VRAG systems interleave reasoning with iterative retrieval. However, existing agentic VRAG faces two critical bottlenecks. (1) Visual Evidence Sparsity: key evidence is scattered across pages yet processed in isolation, hindering cross-page reasoning; moreover, fine-grained intra-image evidence often requires precise visual actions, whose misuse degrades retrieval quality; (2) Search Drift in Long Horizons: the accumulation of visual tokens across retrieved pages dilutes context and causes cognitive overload, leading agents to deviate from their search objective. To address these challenges, we propose VISOR (Visual Retrieval-Augmented Generation via Iterative Search and Over-horizon Reasoning), a unified single-agent framework. VISOR features a structured Evidence Space for progressive cross-page reasoning, coupled with a Visual Action Evaluation and Correction mechanism to manage visual actions. Additionally, we introduce a Dynamic Trajectory with Sliding Window and Intent Injection to mitigate search drift. They anchor the evidence space while discarding earlier raw interactions, preventing context from being overwhelmed by visual tokens. We train VISOR using a Group Relative Policy Optimization-based Reinforcement Learning (GRPO-based RL) pipeline with state masking and credit assignment tailored for dynamic context reconstruction. Extensive experiments on ViDoSeek, SlideVQA, and MMLongBench demonstrate that VISOR achieves state-of-the-art performance while maintaining reasonable and controllable computational costs for long-horizon visual reasoning tasks. The source code is available at https://github.com/syc1336/VISOR.

Yucheng Shen, Jiulong Wu, Jizhou Huang +3

Soochow University, Suzhou, Jiangsu, China · Baidu Inc., Beijing, China

Agentic RAG Multimodal RAG Visual Reasoning Document QA

Apr 10, 2026

MAB-DQA: Addressing Query Aspect Importance in Document Question Answering with Multi-Armed Bandits

Document Question Answering (DQA) involves generating answers from a document based on a user's query, representing a key task in document understanding. This task requires interpreting visual layouts, which has prompted recent studies to adopt multimodal Retrieval-Augmented Generation (RAG) that processes page images for answer generation. However, in multimodal RAG, visual DQA struggles to utilize a large number of images effectively, as the retrieval stage often retains only a few candidate pages (e.g., Top-4), causing informative but less visually salient content to be overlooked in favor of common yet low-information pages. To address this issue, we propose a Multi-Armed Bandit-based DQA framework (MAB-DQA) to explicitly model the varying importance of multiple implicit aspects in a query. Specifically, MAB-DQA decomposes a query into aspect-aware subqueries and retrieves an aspect-specific candidate set for each. It treats each subquery as an arm and uses preliminary reasoning results from a small number of representative pages as reward signals to estimate aspect utility. Guided by an exploration-exploitation policy, MAB-DQA dynamically reallocates retrieval budgets toward high-value aspects. With the most informative pages and their correlations, MAB-DQA generates the expected results. On four benchmarks, MAB-DQA shows an average improvement of 5%-18% over the state-of-the-art method, consistently enhancing document understanding. Codes are available at https://github.com/ElephantOH/MAB-DQA.

Yixin Xiang, Yunshan Ma, Xiaoyu Du +3

Nanjing University of Science and Technology · Singapore Management University · Nanjing Pami Intelligent Technology Co., Ltd. +2

Document QA Multimodal RAG

Apr 6, 2026

GROUNDEDKG-RAG: Grounded Knowledge Graph Index for Long-document Question Answering

Retrieval-augmented generation (RAG) systems have been widely adopted in contemporary large language models (LLMs) due to their ability to improve generation quality while reducing the required input context length. In this work, we focus on RAG systems for long-document question answering. Current approaches suffer from a heavy reliance on LLM descriptions resulting in high resource consumption and latency, repetitive content across hierarchical levels, and hallucinations due to no or limited grounding in the source text. To improve both efficiency and factual accuracy through grounding, we propose GroundedKG-RAG, a RAG system in which the knowledge graph is explicitly extracted from and grounded in the source document. Specifically, we define nodes in GroundedKG as entities and actions, and edges as temporal or semantic relations, with each node and edge grounded in the original sentences. We construct GroundedKG from semantic role labeling (SRL) and abstract meaning representation (AMR) parses and then embed it for retrieval. During querying, we apply the same transformation to the query and retrieve the most relevant sentences from the grounded source text for question answering. We evaluate GroundedKG-RAG on examples from the NarrativeQA dataset and find that it performs on par with a state-of-the art proprietary long-context model at smaller cost and outperforms a competitive baseline. Additionally, our GroundedKG is interpretable and readable by humans, facilitating auditing of results and error analysis.

Tianyi Zhang, Andreas Marfurt

getAbstract · Lucerne University of Applied Sciences and Arts Switzerland

Question Answering Document QA Graph Retrieval-Augmented Generation LLM Grounding KG Construction

Mar 31, 2026

Long-Document QA with Chain-of-Structured-Thought and Fine-Tuned SLMs

Large language models (LLMs) are widely applied to data analytics over documents, yet direct reasoning over long, noisy documents remains brittle and error-prone. Hence, we study document question answering (QA) that consolidates dispersed evidence into a structured output (e.g., a table, graph, or chunks) to support reliable, verifiable QA. We propose a two-pillar framework, LiteCoST, to achieve both high accuracy and low latency with small language models (SLMs). Pillar 1: Chain-of-Structured-Thought (CoST). We introduce a CoST template, a schema-aware instruction that guides a strong LLM to produce both a step-wise CoST trace and the corresponding structured output. The process induces a minimal structure, normalizes entities/units, aligns records, serializes the output, and verifies/refines it, yielding auditable supervision. Pillar 2: SLM fine-tuning. The compact models are trained on LLM-generated CoST data in two stages: Supervised Fine-Tuning for structural alignment, followed by Group Relative Policy Optimization (GRPO) incorporating triple rewards for answer/format quality and process consistency. By distilling structure-first behavior into SLMs, this approach achieves LLM-comparable quality on multi-domain long-document QA using 3B/7B SLMs, while delivering 2-4x lower latency than GPT-4o and DeepSeek-R1 (671B). The code is available at https://github.com/HKUSTDial/LiteCoST.

Zhuowen Liang, Xiaotian Lin, Zhengxuan Zhang +3

The Hong Kong University of Science and Technology (Guangzhou) · EvenUp, USA

Question Answering Document QA LLM Prompting LLM Fine-Tuning

Mar 30, 2026

From PDF to RAG-Ready: Evaluating Document Conversion Frameworks for Domain-Specific Question Answering

Retrieval-Augmented Generation (RAG) systems depend critically on the quality of document preprocessing, yet no prior study has evaluated PDF processing frameworks by their impact on downstream question-answering accuracy. We address this gap through a systematic comparison of four open-source PDF-to-Markdown conversion frameworks, Docling, MinerU, Marker, and DeepSeek OCR, across 21 pipeline configurations, varying the conversion tool, cleaning transformations, splitting strategy, and metadata enrichment. Evaluation was performed using a 50-question benchmark over a corpus of 36 Portuguese administrative documents (1706 pages, ~492K words), with LLM-as-judge scoring over 50 independent runs per configuration. Statistical significance was assessed via Wilcoxon signed-rank tests with Cohen's d effect sizes. Two baselines bounded the results: naïve PDFLoader (86.2%) and manually curated Markdown (91.3%). Docling with hierarchical splitting and image descriptions achieved the highest automated accuracy (94.1 +/- 1.6%), surpassing even manual curation. A per-question-type analysis revealed that table-dependent questions drive the largest accuracy differences, with a 33-percentage-point gap between basic and hierarchical splitting. Metadata enrichment and hierarchy-aware chunking contributed more to accuracy than the conversion framework alone. An exploratory GraphRAG implementation underperformed basic RAG (82% vs. 94.1%). These findings demonstrate that data preparation quality is the dominant factor in RAG system performance.

José Guilherme Marques dos Santos, Ricardo Yang, Rui Humberto Pereira +8

Faculty of Engineering, University of Porto, 4200-465 Porto, Portugal · Department of Business Administration, University of Maia, 4475-690 Maia, Portugal · LIACC—Artificial Intelligence and Computer Science Laboratory, University of Porto, 4200-465 Porto, Portugal +3

Document Parsing RAG Evaluation Document QA Document Chunking

Mar 28, 2026

EuraGovExam: A Multilingual Multimodal Benchmark from Real-World Civil Service Exams

We present EuraGovExam, a multilingual and multimodal benchmark sourced from real-world civil service examinations across five representative Eurasian regions: South Korea, Japan, Taiwan, India, and the European Union. Designed to reflect the authentic complexity of public-sector assessments, the dataset contains over 8,000 high-resolution scanned multiple-choice questions covering 17 diverse academic and administrative domains. Unlike existing benchmarks, EuraGovExam embeds all question content--including problem statements, answer choices, and visual elements--within a single image, providing only a minimal standardized instruction for answer formatting. This design demands that models perform layout-aware, cross-lingual reasoning directly from visual input. All items are drawn from real exam documents, preserving rich visual structures such as tables, multilingual typography, and form-like layouts. Evaluation results show that even state-of-the-art vision-language models (VLMs) achieve only 86% accuracy, underscoring the benchmark's difficulty and its power to diagnose the limitations of current models. By emphasizing cultural realism, visual complexity, and linguistic diversity, EuraGovExam establishes a new standard for evaluating VLMs in high-stakes, multilingual, image-grounded settings. It also supports practical applications in e-governance, public-sector document analysis, and equitable exam preparation.

Jaeseong Kim, Chaehwan Lim, Sang Hyun Gil +1

School of Computer Science / Data Intelligence Lab, Semyung University, Jecheon, Republic of Korea

Multilingual VLM Evaluation Multimodal QA Multilingual QA Document QA

Mar 25, 2026

Chronological Knowledge Retrieval: A Retrieval-Augmented Generation Approach to Construction Project Documentation

In large-scale construction projects, the continuous evolution of decisions generates extensive records, most often captured in meeting minutes. Since decisions may override previous ones, professionals often need to reconstruct the history of specific choices. Retrieving such information manually from raw archives is both labor-intensive and error-prone. From a user perspective, we address this challenge by enabling conversational access to the whole set of project meeting minutes. Professionals can pose natural-language questions and receive answers that are both semantically relevant and explicitly time-annotated, allowing them to follow the chronology of decisions. From a technical perspective, our solution employs a Retrieval-Augmented Generation (RAG) framework that integrates semantic search with large language models to ensure accurate and context-aware responses. We demonstrate the approach using an anonymized, industry-sourced dataset of meeting minutes from a completed construction project by a large company in Belgium. The dataset is annotated and enriched with expert-defined queries to support systematic evaluation. Both the dataset and the open-source implementation are made available to the community to foster further research on conversational access to time-annotated project documentation.

Ioannis-Aris Kostis, Natalia Sanchiz, Steeve De Schryver +2

Université Catholique de Louvain, ICTEAM/INGI, Place Sainte Barbe 2, Louvain-la-Neuve, 1348, Belgium · Buildwise, Avenue P. Holoﬀe 21, Limelette, 1342, Belgium · BPC Group, Avenue Edmond Van Nieuwenhuyse 30, Brussels, 1160, Belgium

Document QA Temporal QA Historical Document Processing

Mar 20, 2026

FDARxBench: Benchmarking Regulatory and Clinical Reasoning on FDA Generic Drug Assessment

We introduce an expert curated, real-world benchmark for evaluating document-grounded question-answering (QA) motivated by generic drug assessment, using the U.S. Food and Drug Administration (FDA) drug label documents. Drug labels contain rich but heterogeneous clinical and regulatory information, making accurate question answering difficult for current language models. In collaboration with FDA regulatory assessors, we introduce FDARxBench, and construct a multi-stage pipeline for generating high-quality, expert curated, QA examples spanning factual, multi-hop, and refusal tasks, and design evaluation protocols to assess both open-book and closed-book reasoning. Experiments across proprietary and open-weight models reveal substantial gaps in factual grounding, long-context retrieval, and safe refusal behavior. While motivated by FDA generic drug assessment needs, this benchmark also provides a substantial foundation for challenging regulatory-grade evaluation of label comprehension. The benchmark is designed to support evaluation of LLM behavior on drug-label questions.

Betty Xiong, Jillian Fisher, Benjamin Newman +5

Stanford University · University of Washington · U.S. Food and Drug Administration

Document QA Medical QA Healthcare

Mar 13, 2026

ESG-Bench: Benchmarking Long-Context ESG Reports for Hallucination Mitigation

As corporate responsibility increasingly incorporates environmental, social, and governance (ESG) criteria, ESG reporting is becoming a legal requirement in many regions and a key channel for documenting sustainability practices and assessing firms' long-term and ethical performance. However, the length and complexity of ESG disclosures make them difficult to interpret and automate the analysis reliably. To support scalable and trustworthy analysis, this paper introduces ESG-Bench, a benchmark dataset for ESG report understanding and hallucination mitigation in large language models (LLMs). ESG-Bench contains human-annotated question-answer (QA) pairs grounded in real-world ESG report contexts, with fine-grained labels indicating whether model outputs are factually supported or hallucinated. Framing ESG report analysis as a QA task with verifiability constraints enables systematic evaluation of LLMs' ability to extract and reason over ESG content and provides a new use case: mitigating hallucinations in socially sensitive, compliance-critical settings. We design task-specific Chain-of-Thought (CoT) prompting strategies and fine-tune multiple state-of-the-art LLMs on ESG-Bench using CoT-annotated rationales. Our experiments show that these CoT-based methods substantially outperform standard prompting and direct fine-tuning in reducing hallucinations, and that the gains transfer to existing QA benchmarks beyond the ESG domain.

Siqi Sun, Ben Peng Wu, Mali Jin +3

School of Computer Science, University of Sheffield, Sheffield, UK

LLM Hallucination Mitigation LLM Safety Benchmarks Document QA Long-Context QA

Mar 12, 2026

Strategic Navigation or Stochastic Search? How Agents and Humans Reason Over Document Collections

Multimodal agents offer a promising path to automating complex document-intensive workflows. Yet, a critical question remains: do these agents demonstrate genuine strategic reasoning, or merely stochastic trial-and-error search? To address this, we introduce MADQA, a benchmark of 2,250 human-authored questions grounded in 800 heterogeneous PDF documents. Guided by Classical Test Theory, we design it to maximize discriminative power across varying levels of agentic abilities. To evaluate agentic behaviour, we introduce a novel evaluation protocol measuring the accuracy-effort trade-off. Using this framework, we show that while the best agents can match human searchers in raw accuracy, they succeed on largely different questions and rely on brute-force search to compensate for weak strategic planning. They fail to close the nearly 20% gap to oracle performance, persisting in unproductive loops. We release the dataset and evaluation harness to help facilitate the transition from brute-force retrieval to calibrated, efficient reasoning.

Łukasz Borchmann, Jordy Van Landeghem, Michał Turski +12

Multi-Document QA LLM Agent Evaluation Multimodal Search Agents AI Agent Benchmarks Document QA IR Evaluation

Mar 11, 2026

Citation-Enforced RAG for Fiscal Document Intelligence: Cited, Explainable Knowledge Retrieval in Tax Compliance

Tax authorities and public-sector financial agencies rely on large volumes of unstructured and semi-structured fiscal documents - including tax forms, instructions, publications, and jurisdiction-specific guidance - to support compliance analysis and audit workflows. While recent advances in generative AI and retrieval-augmented generation (RAG) have shown promise for document-centric question answering, existing approaches often lack the transparency, citation fidelity, and conservative behaviour required in high-stakes regulatory domains. This paper presents a multimodal, citation-enforced RAG framework for fiscal document intelligence that prioritises explainability and auditability. The framework adopts a source-first ingestion strategy, preserves page-level provenance, enforces citations during generation, and supports abstention when evidence is insufficient. Evaluation on real IRS and state tax documents demonstrates improved citation fidelity, reduced hallucination, and analyst-usable explanations, illustrating a pathway toward trustworthy AI for tax compliance.

Akhil Chandra Shanivendra

Independent Researcher

Document QA Knowledge-Intensive QA Explainable Artificial Intelligence RAG Evaluation Data Provenance

Mar 9, 2026

OfficeQA Pro: An Enterprise Benchmark for End-to-End Grounded Reasoning

We introduce OfficeQA Pro, a benchmark for evaluating AI agents on grounded, multi-document reasoning over a large and heterogeneous document corpus. The corpus consists of U.S. Treasury Bulletins spanning nearly 100 years, comprising 89,000 pages and over 26 million numerical values. OfficeQA Pro consists of 133 questions that require precise document parsing, retrieval, and analytical reasoning across both unstructured text and tabular data. Frontier LLMs including Claude Opus 4.6, GPT-5.4, and Gemini 3.1 Pro Preview achieve less than 5% accuracy on OfficeQA Pro when relying on parametric knowledge, and less than 12% with additional access to the web. When provided directly with the document corpus, frontier agents still struggle on over half of questions, scoring 34.1% on average. We find that providing agents with a structured document representation produced by Databricks' ai_parse_document yields a 16.1% average relative performance gain across agents. We conduct additional ablations to study the effects of model selection, table representation, retrieval strategy, and test-time scaling on performance. Despite these improvements, significant headroom remains before agents can be considered reliable at enterprise-grade grounded reasoning.

Krista Opsahl-Ong, Arnav Singhvi, Jasmine Collins +10

Databricks

Multi-Document QA LLM Agent Evaluation AI Agent Benchmarks Document QA LLM Grounding Table QA

Mar 9, 2026

SPD-RAG: Sub-Agent Per Document Retrieval-Augmented Generation

Answering complex, real-world queries often requires synthesizing facts scattered across vast document corpora. In these settings, standard retrieval-augmented generation (RAG) pipelines suffer from incomplete evidence coverage, while long-context large language models (LLMs) struggle to reason reliably over massive inputs. We introduce SPD-RAG, a hierarchical multi-agent framework for exhaustive cross-document question answering that decomposes the problem along the document axis. Each document is processed by a dedicated document-level agent operating only on its own content, enabling focused retrieval, while a coordinator dispatches tasks to relevant agents and aggregates their partial answers. Agent outputs are synthesized by merging partial answers through a token-bounded synthesis layer (which supports recursive map-reduce for massive corpora). This document-level specialization with centralized fusion improves scalability and answer quality in heterogeneous multidocument settings while yielding a modular, extensible retrieval pipeline. On the LOONG benchmark (EMNLP 2024) for long-context multi-document QA, SPD-RAG achieves an Avg Score of 58.1 (GPT-5 evaluation), outperforming Normal RAG (33.0) and Agentic RAG (32.8) while using only 38% of the API cost of a full-context baseline (68.0).

Yagiz Can Akay, Muhammed Yusuf Kartal, Esra Alparslan +2

TOBB University of Economics and Technology · OSTIM Technical University

Multi-Document QA Retrieval-Augmented Generation Agentic RAG Document QA Multi-Agent LLM Systems

Mar 6, 2026

InfoGatherer: Principled Information Seeking via Evidence Retrieval and Strategic Questioning

LLMs are increasingly deployed in high-stakes domains such as medical triage and legal assistance, often as document-grounded QA systems in which a user provides a description, relevant sources are retrieved, and an LLM generates a prediction. In practice, initial user queries are often underspecified, and a single retrieval pass is insufficient for reliable decision-making, leading to incorrect and overly confident answers. While follow-up questioning can elicit missing information, existing methods typically depend on implicit, unstructured confidence signals from the LLM, making it difficult to determine what remains unknown, what information matters most, and when to stop asking questions. We propose InfoGatherer, a framework that gathers missing information from two complementary sources: retrieved domain documents and targeted follow-up questions to the user. InfoGatherer models uncertainty using Dempster-Shafer belief assignments over a structured evidential network, enabling principled fusion of incomplete and potentially contradictory evidence from both sources without prematurely collapsing to a definitive answer. Across legal and medical tasks, InfoGatherer outperforms strong baselines while requiring fewer turns. By grounding uncertainty in formal evidential theory rather than heuristic LLM signals, InfoGatherer moves towards trustworthy, interpretable decision support in domains where reliability is critical.

Maksym Taranukhin, Shuyue Stella Li, Evangelos Milios +3

University of British Columbia · Vector Institute · University of Washington +2

Document QA LLM Decision-Making LLM Uncertainty Estimation Clarification Question Generation Clinical Decision Support

Feb 26, 2026

MoDora: Tree-Based Semi-Structured Document Analysis System

Semi-structured documents integrate diverse interleaved data elements (e.g., tables, charts, hierarchical paragraphs) arranged in various and often irregular layouts. These documents are widely observed across domains and account for a large portion of real-world data. However, existing methods struggle to support natural language question answering over these documents due to three main technical challenges: (1) The elements extracted by techniques like OCR are often fragmented and stripped of their original semantic context, making them inadequate for analysis. (2) Existing approaches lack effective representations to capture hierarchical structures within documents (e.g., associating tables with nested chapter titles) and to preserve layout-specific distinctions (e.g., differentiating sidebars from main content). (3) Answering questions often requires retrieving and aligning relevant information scattered across multiple regions or pages, such as linking a descriptive paragraph to table cells located elsewhere in the document. To address these issues, we propose MoDora, an LLM-powered system for semi-structured document analysis. First, we adopt a local-alignment aggregation strategy to convert OCR-parsed elements into layout-aware components, and conduct type-specific information extraction for components with hierarchical titles or non-text elements. Second, we design the Component-Correlation Tree (CCTree) to hierarchically organize components, explicitly modeling inter-component relations and layout distinctions through a bottom-up cascade summarization process. Finally, we propose a question-type-aware retrieval strategy that supports (1) layout-based grid partitioning for location-based retrieval and (2) LLM-guided pruning for semantic-based retrieval. Experiments show MoDora outperforms baselines by 5.97%-61.07% in accuracy. The code is at https://github.com/weAIDB/MoDora.

Bangrui Xu, Qihang Yao, Zirui Tang +8

Shanghai Jiao Tong University · Microsoft Research · Beihang University +2

Document QA Document Layout Analysis Hybrid Retrieval

Feb 24, 2026

GATES: Self-Distillation under Privileged Context with Consensus Gating

We study self-distillation in settings where supervision is unreliable: there are no ground truth labels, verifiable rewards, or external graders to evaluate answers. We focus on document-grounded question answering with asymmetric context, where a single model serves as both tutor (with access to a relevant source document during training) and student (answering from the question alone at test time). Rather than assuming tutor correctness, we derive supervision online from tutor consensus by sampling multiple document-grounded reasoning traces and using agreement to gate learning. Conditioned on this reliability signal, we distill knowledge through full tutor reasoning trajectories (not just final answers), providing a dense and stable learning signal. Empirically, this consensus-gated trajectory distillation substantially improves transfer to the document-free student. Held-out in-domain accuracy under asymmetric evaluation improves from 46.0% to 62.0%, and average (maj@8) accuracy on public document-free math benchmarks improves from 20.2% to 35.4%.

Alex Stein, Furong Huang, Tom Goldstein

University of Maryland, College Park

Knowledge Distillation On-Policy Self-Distillation Context Distillation CoT Distillation Document QA