MFMDQwen: Multilingual Financial Misinformation Detection Based on Large Language Model

2026-04-20

AI Summary

This study addresses the dual challenges of linguistic diversity and domain complexity in multilingual financial misinformation detection, a task where existing approaches are largely confined to English and single-task settings. To overcome these limitations, this work proposes MFMDQwen—the first multilingual large language model supporting Chinese, English, Greek, and Bengali—leveraging multilingual instruction tuning for cross-lingual financial misinformation identification. Concurrently, the authors introduce and publicly release the first multilingual financial misinformation instruction-tuning dataset, MFMD4Instruction, along with a dedicated evaluation benchmark, MFMDBench. Experimental results demonstrate that MFMDQwen significantly outperforms current open-source models on MFMDBench, confirming its effectiveness and strong generalization capability across languages and financial contexts.

Technology Category

• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)
• Machine Learning: Large Multimodal Models (LMMs)
• Application Domains: Misinformation & Fake News

Application Category

• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

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.

Problem

• Multilingual Financial Misinformation Detection
• Financial Misinformation
• Large Language Model
• Multilingual Context
• Instruction Dataset

Innovation

• Multilingual Financial Misinformation Detection
• Large Language Model
• Instruction Dataset
• Benchmark Dataset
• Open-source LLM