Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Simmering, Paul F., Schulz, Benedikt, Tabino, Oliver, Wittenburg, Georg
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2508.15817
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911116218597376
author Simmering, Paul F.
Schulz, Benedikt
Tabino, Oliver
Wittenburg, Georg
author_facet Simmering, Paul F.
Schulz, Benedikt
Tabino, Oliver
Wittenburg, Georg
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2508_15817
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Meet Your New Client: Writing Reports for AI -- Benchmarking Information Loss in Market Research Deliverables
Simmering, Paul F.
Schulz, Benedikt
Tabino, Oliver
Wittenburg, Georg
Computation and Language
Computers and Society
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.
title Meet Your New Client: Writing Reports for AI -- Benchmarking Information Loss in Market Research Deliverables
topic Computation and Language
Computers and Society
url https://arxiv.org/abs/2508.15817