SHROOM-CAP's Data-Centric Approach to Multilingual Hallucination Detection

This research focuses on a critical problem in LLMs: the generation of factual inaccuracies across multiple languages. The use of XLM-RoBERTa suggests a strong emphasis on leveraging cross-lingual capabilities for effective hallucination detection.

• •Addresses the problem of factual inaccuracies in multilingual LLMs.
• •Employs a data-centric approach for hallucination detection.
• •Utilizes XLM-RoBERTa, leveraging its cross-lingual capabilities.