@inproceedings{zhang-etal-2025-mario,
    title = "{MARIO}-0.5{B}: A Multi-Agent Lightweight Model for Real-Time Open Information Extraction in Low-Resource Settings",
    author = "Zhang, Donghai  and
      Yang, SHuangtao  and
      Xiaozheng, Dong  and
      Song, Wei  and
      Fu, Bo",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.703/",
    doi = "10.18653/v1/2025.findings-emnlp.703",
    pages = "13085--13094",
    ISBN = "979-8-89176-335-7",
    abstract = "Large language models (LLMs) have shown remarkable capabilities in open information extraction. However, their substantial resource requirements often restrict their deployment in resource-constrained industrial settings, particularly on edge devices. The high computational demands also lead to increased latency, making them difficult to apply in real-time applications. In this paper, we introduce MARIO-0.5B, an ultra-lightweight model trained on instruction-based samples in Chinese, English, Korean, and Russian. We also present a novel multi-agent framework, SMOIE, which integrates schema mining, information extraction, reasoning, and decision-making to effectively support MARIO-0.5B.The experimental results show that our framework outperforms large-scale models with up to 70B parameters, reducing computational resources by 140x and delivering 11x faster response times. Moreover, it operates efficiently in CPU-only environments, which makes it well-suited for widespread industrial deployment."
}