Xiaozhong Liu

Xiaozhong Liu

Auto-generated profile, based on publicly available information

Xiaozhong Liu

Worcester Polytechnic Institute, Worcester, MA, USA

Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2023
Verified
Conference Paper
Open access
PDF file
YWYiquan Wu
Yiquan Wu
SZSiying Zhou
Siying Zhou
YLYifei Liu
Yifei Liu
WLWeiming Lu
Weiming Lu
XLXiaozhong Liu
Xiaozhong Liu
KKKun Kuang
Kun Kuang
Yiquan Wu, Siying Zhou, Yifei Liu, Weiming Lu, Xiaozhong Liu, Yating Zhang, Changlong Sun, Fei Wu, Kun Kuang. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. 2023.

1 January 2024
Verified
Conference Paper
Open access
PDF file
WYWeikang Yuan
Weikang Yuan
JCJunjie Cao
Junjie Cao
ZJZhuoren Jiang
Zhuoren Jiang
YKYangyang Kang
Yangyang Kang
JLJun Lin
Jun Lin
XLXiaozhong Liu
Xiaozhong Liu
Weikang Yuan, Junjie Cao, Zhuoren Jiang, Yangyang Kang, Jun Lin, Kaisong Song, Tianqianjin Lin, Pengwei Yan, Changlong Sun, Xiaozhong Liu. Findings of the Association for Computational Linguistics: EMNLP 2024. 2024.

12 February 2023 in arXiv
Verified
Preprint
Open access
PDF file
YMYongqiang Ma
Yongqiang Ma
JLJiawei Liu
Jiawei Liu
FYFan Yi
Fan Yi
QCQikai Cheng
Qikai Cheng
YHYong Huang
Yong Huang
XLXiaozhong Liu
Xiaozhong Liu
Recent neural language models have taken a significant step forward in producing remarkably controllable, fluent, and grammatical text. Although studies have found that AI-generated text is not distinguishable from human-written text for crowd-sourcing workers, there still exist errors in AI-generated text which are even subtler and harder to spot. We primarily focus on the scenario in which scientific AI writing assistant is deeply involved. First, we construct a feature description framework to distinguish between AI-generated text and human-written text from syntax, semantics, and pragmatics based on the human evaluation. Then we utilize the features, i.e., writing style, coherence, consistency, and argument logistics, from the proposed framework to analyze two types of content. Finally, we adopt several publicly available methods to investigate the gap of between AI-generated scientific text and human-written scientific text by AI-generated scientific text detection models. The results suggest that while AI has the potential to generate scientific content that is as accurate as human-written content, there is still a gap in terms of depth and overall quality. The AI-generated scientific content is more likely to contain errors in factual issues. We find that there exists a "writing style" gap between AI-generated scientific text and human-written scientific text. Based on the analysis result, we summarize a series of model-agnostic and distribution-agnostic features for detection tasks in other domains. Findings in this paper contribute to guiding the optimization of AI models to produce high-quality content and addressing related ethical and security concerns.

4 December 2023 in Information Processing & Management
Verified
Journal Article
Closed access
TLTianqianjin Lin
Tianqianjin Lin
KSKaisong Song
Kaisong Song
ZJZhuoren Jiang
Zhuoren Jiang
YKYangyang Kang
Yangyang Kang
WYWeikang Yuan
Weikang Yuan
XLXiaozhong Liu
Xiaozhong Liu

6 March 2013 in Scientometrics
Verified
Journal Article
Closed access
PDF file
LLLili Lin
Lili Lin
ZXZhuoming Xu
Zhuoming Xu
YDYing Ding
Ying Ding
XLXiaozhong Liu
Xiaozhong Liu

1 January 2023
Verified
Conference Paper
Open access
PDF file
KPKaihang Pan
Kaihang Pan
JLJuncheng Li
Juncheng Li
HSHongye Song
Hongye Song
JLJun Lin
Jun Lin
XLXiaozhong Liu
Xiaozhong Liu
STSiliang Tang
Siliang Tang
Kaihang Pan, Juncheng Li, Hongye Song, Jun Lin, Xiaozhong Liu, Siliang Tang. Findings of the Association for Computational Linguistics: EMNLP 2023. 2023.