Researchers introduced MAWARITH, a new dataset containing 12,500 annotated Arabic inheritance cases to assess large language models' ability to perform complex legal reasoning in Islamic inheritance law. The dataset and its associated evaluation metric MIR-E highlight significant challenges for current LLMs in accurately identifying heirs, applying rules correctly, and calculating exact shares, emphasizing the need for improved reasoning capabilities in legal contexts.
Read the full article at arXiv cs.CL (NLP)
Want to create content about this topic? Use Nemati AI tools to generate articles, social posts, and more.
14
Comments
Ali NematiWritten by Ali
