REVIEW 26 cited by
Docling Technical Report
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Docling Technical Report
read the original abstract
This technical report introduces Docling, an easy to use, self-contained, MIT-licensed open-source package for PDF document conversion. It is powered by state-of-the-art specialized AI models for layout analysis (DocLayNet) and table structure recognition (TableFormer), and runs efficiently on commodity hardware in a small resource budget. The code interface allows for easy extensibility and addition of new features and models.
Forward citations
Cited by 26 Pith papers
-
Can Coding Agents Reproduce Findings in Computational Materials Science?
AutoMat benchmark shows current LLM coding agents achieve at most 54.1% success when reproducing computational materials science claims from papers.
-
The Documentation and Traceability Burden of the Indian EV Transition
The paper systematises India's EV compliance-document lifecycle into a two-layer evidence model, a six-stage lifecycle with four failure loci, an exergy-destruction analytic lens, and a six-problem research agenda.
-
LLM-Based Examination of Eligibility Criteria from Securities Prospectuses at the German Central Bank
LLMs are applied in a generative pipeline for extracting, normalizing, and interpreting eligibility criteria from securities prospectuses, achieving up to 91% precision in document-level decisions with a conservative bias.
-
RealDocBench: A Benchmark for Field-Level QA and Layout Understanding on Real-World Regulated Documents
RealDocBench supplies 1,356 field-level QA questions over 581 real documents and 1,500 annotated pages, evaluating 18 systems on per-field accuracy, cost, and latency.
-
Benchmarking Complex Multimodal Document Processing Pipelines: A Unified Evaluation Framework for Enterprise AI
EnterpriseDocBench shows hybrid retrieval edges out BM25 and dense embeddings in end-to-end document pipelines, with weak inter-stage correlations and a gap between 85.5% factual accuracy and 0.40 average completeness.
-
From PDF to RAG-Ready: Evaluating Document Conversion Frameworks for Domain-Specific Question Answering
Docling with hierarchical splitting reaches 94.1% RAG accuracy on domain documents, beating naive PDF loading but trailing manual Markdown curation at 97.1%.
-
Guided Query Refinement: Multimodal Hybrid Retrieval with Test-Time Optimization
GQR is a test-time optimization technique that refines primary retriever query embeddings using complementary retriever scores to achieve high performance with smaller representations in multimodal visual document retrieval.
-
Scientific Code Search at Scale: A Multi-Domain Dataset and Benchmark
A multi-domain corpus of 5,264 scientific GitHub repos plus two IR benchmarks (219 expert queries; 117,950 snippets / 119,720 queries) shows large domain- and documentation-driven gaps in scientific code search.
-
OmniPresent: Generating Coherent Presentation Suites from Scientific Papers
A multi-agent HTML pipeline with shared knowledge and cross-artifact verify-and-repair generates coherent poster/slides/video/page suites from papers and beats specialized baselines on OmniPreBench.
-
DocAtlas: Multilingual Document Understanding Across 80+ Languages
DocAtlas creates multilingual document datasets across 82 languages and shows DPO with rendered ground truth improves model accuracy by 1.7-1.9% without degrading base-language performance, unlike supervised fine-tuning.
-
DocAtlas: Multilingual Document Understanding Across 80+ Languages
DocAtlas introduces model-free rendering pipelines to create DocTag-annotated datasets across 82 languages and shows DPO adaptation improves multilingual performance without base-language degradation.
-
Measuring research data reuse in scholarly publications using generative artificial intelligence: Open Science Indicator development and preliminary results
A fine-tuned LLM with a verifier labels 43% of 4,475 PLOS Q1-2024 articles as reusing existing research data, more than double the rate detected by bibliometric methods.
-
Generating Verifiable Chain of Thoughts from Exection-Traces
A pipeline produces 54,000 execution-trace-verified bi-directional Chain-of-Thought rationales for code, and fine-tuning on them yields gains up to 26.6 points on LiveCodeBench-Exec and similar benchmarks.
-
Benchmarking Table Extraction from Heterogeneous Scientific PDF Documents
A new benchmark with two new datasets and end-to-end metrics shows that table extraction from PDFs is still unreliable across heterogeneous layouts.
-
SlideAgent: Hierarchical Agentic Framework for Multi-Page Visual Document Understanding
SARA combines natural-language snippets with semantic compression vectors in RAG to improve answer relevance, correctness, and similarity on 9 datasets across 5 LLMs.
-
SlideAgent: Hierarchical Agentic Framework for Multi-Page Visual Document Understanding
A three-level hierarchical agent framework for slide QA improves accuracy by 7.9–9.8 points over its base LLM across multiple slide benchmarks.
-
Improving Access to Historical Archives with Real-time RAG-based Systems
LLM post-OCR cleanup plus dense retrieval and cross-encoder reranking raises NDCG@10 by 31.9% over BM25 on 500k Swiss newspaper segments while cutting CER/WER substantially.
-
An AI-ready, Polarized Electron-Positron Collision Dataset
Release of an AI-ready dataset containing approximately 660,000 reconstructed polarized e+e- collision events at 91.2 GeV from the SLD experiment, translated from legacy formats with accompanying digitized documentation.
-
Measuring research data reuse in scholarly publications using generative artificial intelligence: Open Science Indicator development and preliminary results
An LLM-powered indicator measures research data reuse at 43% in publications, exceeding rates from established bibliometric methods and implying that benefits of data sharing are currently underestimated.
-
HalluCiteChecker: A Lightweight Toolkit for Hallucinated Citation Detection and Verification in the Era of AI Scientists
HalluCiteChecker is a lightweight, offline, CPU-only toolkit that detects hallucinated citations in AI-assisted scientific papers.
-
From PDF to RAG-Ready: Evaluating Document Conversion Frameworks for Domain-Specific Question Answering
Docling with hierarchical splitting and image descriptions reaches 94.1% RAG QA accuracy on Portuguese admin PDFs, beating manual Markdown and other open-source converters.
-
MimirRAG: A Multi-Agent RAG Framework for Financial Data Retrieval with Metadata Integration
MimirRAG, a multi-agent RAG framework with metadata integration and table-aware chunking, reaches 89.3% accuracy on FinanceBench and outperforms prior baselines for financial document retrieval.
-
RADIANT-LLM: an Agentic Retrieval Augmented Generation Framework for Reliable Decision Support in Safety-Critical Nuclear Engineering
RADIANT-LLM is a local-first multi-modal RAG system with provenance tracking that delivers lower hallucination rates than general LLMs on nuclear engineering benchmarks.
-
Operationalizing Document AI: A Microservice Architecture for OCR and LLM Pipelines in Production
Describes a microservice architecture for production document AI pipelines with OCR and LLMs, reporting that OCR dominates latency and GPU inference capacity limits concurrency.
-
Qwen Goes Brrr: Off-the-Shelf RAG for Ukrainian Multi-Domain Document Understanding
A RAG pipeline with contextual PDF chunking, question-and-answer-aware retrieval and reranking using Qwen3 models reaches 0.96 accuracy on a Ukrainian multi-domain document QA shared task.
-
Causal Connections: Leveraging Multilingual Fine-Tuning for Financial QA@FinCausal 2026
Fine-tuned multilingual LLMs achieve top shared-task scores on financial causality extraction in English and Spanish.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.