Högskolan i Skövde

his.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • apa-cv
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Autonomous data extraction - beyond RAG: Evaluating RAG strategies and model performance in autonomous information extraction
University of Skövde, School of Informatics.
University of Skövde, School of Informatics.
2025 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
Abstract [en]

Regulatory compliance is a complex and resource-intensive framework in the banking and financial sector, comprising multiple use cases. This research focuses on one of its most foundational and labour-intensive components: information extraction from annual reports. In collaboration with an international bank, the study investigates the automation of this process using advanced Retrieval-Augmented Generation (RAG) techniques. Specifically, it evaluates the emerging paradigm of Agentic RAG in comparison to traditional RAG workflows. The research further benchmarks the performance of leading foundation models; Mistral, OpenAI, and LLaMA within the RAG pipeline to assess their suitability for compliance-related document understanding. The primary objective is to determine the effectiveness of autonomous retrieval strategies in enhancing the accuracy and efficiency of ESG data extraction. By aligning cutting-edge developments in agentic AI with real-world industry needs, this study contributes to academic research on intelligent document processing while delivering a practical proof of concept for large-scale regulatory automation.

Place, publisher, year, edition, pages
2025. , p. 1, 35
National Category
Information Systems, Social aspects
Identifiers
URN: urn:nbn:se:his:diva-25596OAI: oai:DiVA.org:his-25596DiVA, id: diva2:1985487
External cooperation
Swedbank
Subject / course
Informationsteknologi
Educational program
Data Science - Master’s Programme
Supervisors
Examiners
Available from: 2025-07-24 Created: 2025-07-24 Last updated: 2025-09-29Bibliographically approved

Open Access in DiVA

fulltext(893 kB)363 downloads
File information
File name FULLTEXT01.pdfFile size 893 kBChecksum SHA-512
feac1d293e62a71e92d6d08efa9770eb2a26a837110e1fa2fd165fff25db89888cd712a6205c1dc29b22e30bd83a76bf8a87ba75ae16bd6634e38ce1e850fab6
Type fulltextMimetype application/pdf

By organisation
School of Informatics
Information Systems, Social aspects

Search outside of DiVA

GoogleGoogle Scholar
Total: 365 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 494 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • apa-cv
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf