Production Systems and Information Engineering
https://ojs.uni-miskolc.hu/index.php/psaie
<p>The aim of the journal is to publish quality research papers on the area of</p> <ul> <li>information engineering</li> <li>software engineering</li> <li>production engineering</li> <li>control engineering</li> <li>applied mathematics</li> <li>logistic information systems</li> </ul>MISKOLC UNIVERSITY PRESSen-USProduction Systems and Information Engineering1785-1270Decision-Rule-Controlled Multi-Agent Validation for Hungarian Banking Complaint Classification
https://ojs.uni-miskolc.hu/index.php/psaie/article/view/4730
<p>This paper presents a decision-rule-controlled multi-agent validation framework for Hungarian banking complaint classification. A previously trained DistilBERT model provides the initial category prediction, while Qwen2.5-7B, Qwen3-8B, and Mistral-7B are used as reasoning and validation agents. A rule-based decision agent determines whether the baseline label is accepted, revised, or routed to exception handling. Experiments were conducted on a 31-category random sample and a reduced Top6 + Exception balanced sample. The results show that unrestricted LLM-based relabeling may significantly degrade performance, while conservative decision rules better preserve baseline stability. The findings indicate that LLMs are more suitable as controlled validation components than as unrestricted classifiers in closed-label banking NLP tasks.</p>Zsolt Krutilla
Copyright (c) 2026 Production Systems and Information Engineering
2026-11-172026-11-1714112610.32968/psaie.2026.1.1.X