MFMDQwen: Multilingual Financial Misinformation Detection Based on Large Language Model

TL;DR

This paper introduces MFMDQwen, an open-source multilingual LLM tailored for financial misinformation detection, supported by new datasets and benchmarks, and demonstrates its superior performance over existing models.

Contribution

The paper presents the first open-source multilingual LLM for MFMD, along with novel datasets and benchmarks to evaluate and improve multilingual financial misinformation detection.

Findings

MFMDQwen outperforms existing open-source LLMs on MFMDBench.

Introduces MFMD4Instruction, a dataset supporting multiple languages for MFMD.

Provides MFMDBench, a benchmark for evaluating multilingual MFMD capabilities.

Abstract

Financial misinformation poses significant threats to financial market stability and individuals' investment decisions. The multilingual environment and the inherent complexity of financial information present substantial challenges for Multilingual Financial Misinformation Detection (MFMD). Existing LLM-based approaches for financial misinformation detection primarily focus on English and a single financial misinformation detection task, which limits their ability to capture multilingual contexts and complex features. In this paper, we propose MFMDQwen, the first open-source LLM designed for MFMD tasks. Furthermore, we introduce MFMD4Instruction, the first instruction dataset supporting MFMD with LLMs, covering English, Chinese, Greek, and Bengali. We also construct MFMDBench, a benchmark dataset for evaluating the MFMD capabilities of LLMs. Experimental results on MFMDBench demonstrate that our model outperforms existing open-source LLMs. The project is available at https://github.com/lzw108/FMD.