This micro-benchmark dataset was made for evaluation of the proposed pipeline in Koletsis et al. Entity Extraction from High-Level CorruptionSchemes via Large Language Models. BDA4FCT@IEEE Big Data 2024. Also available at https://arxiv.org/abs/2409.13704 This dataset comprises 15 articles, totaling 441 sentences, focused on topics related to financial corruption. It includes 2 lists of individuals and organizations mentioned within these articles.

The research leading to these results has received funding from the European Union’s Internal Security Fund under grant agreement No 101103298 (KLEPTOTRACE). This publication reflects only the authors’ views. The European Commission is not responsible for any use that may be made of the information it contains.