Dong Xiaozheng — accepted AI-conference papers

2025

ICLER: Intent CLassification with Enhanced Reasoning

Dezheng Gao, Dong Xiaozheng, SHuangtao Yang, Bo Fu

EMNLP 2025

In recent years, intent classification technology based on In-Context Learning (ICL) has made significant progress. However, when applied to enterprise vertical domains, existing methods are inadequate in identifying micro-grained intentions. This study identifies two primary causes of errors in dat

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

MARIO-0.5B: A Multi-Agent Lightweight Model for Real-Time Open Information Extraction in Low-Resource Settings

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

EMNLP 2025

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 incr

Cited by 0 Source ↗PDF ↗Scholar ↗