mlsanityData to 14 Oct 2026

Meet Your New Client: Writing Reports for AI -- Benchmarking Information Loss in Market Research Deliverables

arXiv 2508.15817 ↗First posted 17 Aug 2025cs.CL cs.CYcited by 1

On the map: Retrieval-augmented generation → RAG pipeline design and evaluation

Abstract (arXiv)

As organizations adopt retrieval-augmented generation (RAG) for their knowledge management systems (KMS), traditional market research deliverables face new functional demands. While PDF reports and slides have long served human readers, they are now also "read" by AI systems to answer user questions. To future-proof reports being delivered today, this study evaluates information loss during their ingestion into RAG systems. It compares how well PDF and PowerPoint (PPTX) documents converted to Markdown can be used by an LLM to answer factual questions in an end-to-end benchmark. Findings show that while text is reliably extracted, significant information is lost from complex objects like charts and diagrams. This suggests a need for specialized, AI-native deliverables to ensure research insights are not lost in translation.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in RAG pipeline design and evaluation, one of 15 directions in Retrieval-augmented generation. Builds on 13 of its 19 references that are in the map. First posted on arXiv 17 Aug 2025.

Builds on

13 of 19 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025A Survey on Knowledge-Oriented Retrieval-Augmented Generation11 Mar
  2. 2023Retrieval-Augmented Generation for Large Language Models: A Survey18 Dec

Other references · 11

  1. 2024Qwen2.5 Technical Reportcited by 4,942
  2. 2024GPT-4o System Cardcited by 4,588
  3. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  4. 2019PlotQA: Reasoning over Scientific Plotscited by 321
  5. 2023FinanceBench: A New Benchmark for Financial Question Answeringcited by 270
  6. 2020HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Datacited by 264
  7. 2024OmniDocBench: Benchmarking Diverse PDF Document Parsing with Comprehensive Annotationscited by 150
  8. 2021QA Dataset Explosion: A Taxonomy of NLP Resources for Question Answering and Reading Comprehensioncited by 91
  9. 2025Docling: An Efficient Open-Source Toolkit for AI-driven Document Conversioncited by 63
  10. 2022Modern Question Answering Datasets and Benchmarks: A Surveycited by 23
  11. 2025MDEval: Evaluating and Enhancing Markdown Awareness in Large Language Modelscited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026PeerPrism: Peer Evaluation Expertise vs Review-writing AIcited by 4

Similar, not cited

Close in wording, no citation either way

  1. 2025Retrieval-Augmented Generation in Industry: An Interview Study on Use Cases, Requirements, Challenges, and Evaluation
  2. 2024Deploying Large Language Models With Retrieval Augmented Generation
  3. 2024Developing Retrieval Augmented Generation (RAG) based LLM Systems from PDFs: An Experience Report
  4. 2025An Agile Method for Implementing Retrieval Augmented Generation Tools in Industrial SMEs
  5. 2025The Budget AI Researcher and the Power of RAG Chains
  6. 2024Optimizing and Evaluating Enterprise Retrieval-Augmented Generation (RAG): A Content Design Perspective
  7. 2025A Systematic Literature Review of Retrieval-Augmented Generation: Techniques, Metrics, and Challenges
  8. 2026EnterpriseRAG-Bench: A RAG Benchmark for Company Internal Knowledge