no code implementations • 13 Apr 2024 • Feihu Jiang, Chuan Qin, Jingshuai Zhang, Kaichun Yao, Xi Chen, Dazhong Shen, Chen Zhu, HengShu Zhu, Hui Xiong
In the contemporary era of widespread online recruitment, resume understanding has been widely acknowledged as a fundamental and crucial task, which aims to extract structured information from resume documents automatically.
no code implementations • 10 Apr 2024 • Feihu Jiang, Chuan Qin, Kaichun Yao, Chuyu Fang, Fuzhen Zhuang, HengShu Zhu, Hui Xiong
For the generation process, we propose a novel chain of thought (CoT) based fine-tuning method to empower the LLM-based generator to adeptly respond to user questions using retrieved documents.
1 code implementation • 18 May 2023 • Chenguang Du, Kaichun Yao, HengShu Zhu, Deqing Wang, Fuzhen Zhuang, Hui Xiong
However, existing HGNNs usually represent each node as a single vector in the multi-layer graph convolution calculation, which makes the high-level graph convolution layer fail to distinguish information from different relations and different orders, resulting in the information loss in the message passing.