2025.findings-emnlp.703@ACL

Total: 1

#1 MARIO-0.5B: A Multi-Agent Lightweight Model for Real-Time Open Information Extraction in Low-Resource Settings [PDF] [Copy] [Kimi] [REL]

Authors: Donghai Zhang, SHuangtao Yang, Dong Xiaozheng, Wei Song, Bo Fu

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.

Subject: EMNLP.2025 - Findings