Comparing Open-Source and Commercial LLMs for Domain-Specific Analysis and Reporting: Software Engineering Challenges and Design Trade-offs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Koraag, Theo, Wagner, Niklas, Dobslaw, Felix, Gren, Lucas
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918150433406976
author Koraag, Theo
Wagner, Niklas
Dobslaw, Felix
Gren, Lucas
author_facet Koraag, Theo
Wagner, Niklas
Dobslaw, Felix
Gren, Lucas
contents Context: Large Language Models (LLMs) enable automation of complex natural language processing across domains, but research on domain-specific applications like Finance remains limited. Objectives: This study explored open-source and commercial LLMs for financial report analysis and commentary generation, focusing on software engineering challenges in implementation. Methods: Using Design Science Research methodology, an exploratory case study iteratively designed and evaluated two LLM-based systems: one with local open-source models in a multi-agent workflow, another using commercial GPT-4o. Both were assessed through expert evaluation of real-world financial reporting use cases. Results: LLMs demonstrated strong potential for automating financial reporting tasks, but integration presented significant challenges. Iterative development revealed issues including prompt design, contextual dependency, and implementation trade-offs. Cloud-based models offered superior fluency and usability but raised data privacy and external dependency concerns. Local open-source models provided better data control and compliance but required substantially more engineering effort for reliability and usability. Conclusion: LLMs show strong potential for financial reporting automation, but successful integration requires careful attention to architecture, prompt design, and system reliability. Implementation success depends on addressing domain-specific challenges through tailored validation mechanisms and engineering strategies that balance accuracy, control, and compliance.
format Preprint
id arxiv_https___arxiv_org_abs_2509_24344
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Comparing Open-Source and Commercial LLMs for Domain-Specific Analysis and Reporting: Software Engineering Challenges and Design Trade-offs
Koraag, Theo
Wagner, Niklas
Dobslaw, Felix
Gren, Lucas
Software Engineering
Context: Large Language Models (LLMs) enable automation of complex natural language processing across domains, but research on domain-specific applications like Finance remains limited. Objectives: This study explored open-source and commercial LLMs for financial report analysis and commentary generation, focusing on software engineering challenges in implementation. Methods: Using Design Science Research methodology, an exploratory case study iteratively designed and evaluated two LLM-based systems: one with local open-source models in a multi-agent workflow, another using commercial GPT-4o. Both were assessed through expert evaluation of real-world financial reporting use cases. Results: LLMs demonstrated strong potential for automating financial reporting tasks, but integration presented significant challenges. Iterative development revealed issues including prompt design, contextual dependency, and implementation trade-offs. Cloud-based models offered superior fluency and usability but raised data privacy and external dependency concerns. Local open-source models provided better data control and compliance but required substantially more engineering effort for reliability and usability. Conclusion: LLMs show strong potential for financial reporting automation, but successful integration requires careful attention to architecture, prompt design, and system reliability. Implementation success depends on addressing domain-specific challenges through tailored validation mechanisms and engineering strategies that balance accuracy, control, and compliance.
title Comparing Open-Source and Commercial LLMs for Domain-Specific Analysis and Reporting: Software Engineering Challenges and Design Trade-offs
topic Software Engineering
url https://arxiv.org/abs/2509.24344