Team FMD LLM at the Financial Misinformation Detection Challenge Task: Exploring Task Structuring and Metadata Impact on Performance

AbstractThe detection of financial misinformation (FMD) is a growing challenge. In this paper, we investigate how task structuring and metadata integration impact the performance of large language models (LLMs) on FMD tasks. We compare two approaches: predicting the label before generating an explanation, and generating the explanation first. Our results reveal that prediction-first models achieve higher F1 scores. We also assess the effect of auxiliary metadata, which surprisingly degraded performance despite its correlation with the labels. Our findings highlight the importance of task order and the need to carefully consider whether to use metadata in limited data settings.