Wenxiong Liao

Wenxiong Liao

Auto-generated profile, based on publicly available information

Wenxiong Liao

School of Computer Science and Engineering, South China University of Technology, Guangzhou, China

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
30 January 2025 in IEEE Transactions on Big Data
Verified
Journal Article
Closed access
HDHaixing Dai
Haixing Dai
ZLZhengliang Liu
Zhengliang Liu
WLWenxiong Liao
Wenxiong Liao
XHXiaoke Huang
Xiaoke Huang
YCYihan Cao
Yihan Cao
Xiang LiXiang Li
Xiang Li
Text data augmentation is an effective strategy for overcoming the challenge of limited sample sizes in many natural language processing (NLP) tasks. This challenge is especially prominent in the few-shot learning (FSL) scenario, where the data in the target domain is generally much scarcer and of lowered quality. A natural and widely used strategy to mitigate such challenges is to perform data augmentation to better capture data invariance and increase the sample size. However, current text data augmentation methods either can’t ensure the correct labeling of the generated data (lacking faithfulness), or can’t ensure sufficient diversity in the generated data (lacking compactness), or both. Inspired by the recent success of large language models (LLM), especially the development of ChatGPT, we propose a text data augmentation approach based on ChatGPT (named ”AugGPT”). AugGPT rephrases each sentence in the training samples into multiple conceptually similar but semantically different samples. The augmented samples can then be used in downstream model training. Experiment results on multiple few-shot learning text classification tasks show the superior performance of the proposed AugGPT approach over state-of-the-art text data augmentation methods in terms of testing accuracy and distribution of the augmented samples.

28 December 2023 in JMIR Medical Education
Verified
Journal Article
Open access
WLWenxiong Liao
Wenxiong Liao
ZLZhengliang Liu
Zhengliang Liu
HDHaixing Dai
Haixing Dai
SXShaochen Xu
Shaochen Xu
ZWZihao Wu
Zihao Wu
Xiang LiXiang Li
Xiang Li
Background: Large language models, such as ChatGPT, are capable of generating grammatically perfect and human-like text content, and a large number of ChatGPT-generated texts have appeared on the internet. However, medical texts, such as clinical notes and diagnoses, require rigorous validation, and erroneous medical content generated by ChatGPT could potentially lead to disinformation that poses significant harm to health care and the general public. Objective: This study is among the first on responsible artificial intelligence–generated content in medicine. We focus on analyzing the differences between medical texts written by human experts and those generated by ChatGPT and designing machine learning workflows to effectively detect and differentiate medical texts generated by ChatGPT. Methods: We first constructed a suite of data sets containing medical texts written by human experts and generated by ChatGPT. We analyzed the linguistic features of these 2 types of content and uncovered differences in vocabulary, parts-of-speech, dependency, sentiment, perplexity, and other aspects. Finally, we designed and implemented machine learning methods to detect medical text generated by ChatGPT. The data and code used in this paper are published on GitHub. Results: Medical texts written by humans were more concrete, more diverse, and typically contained more useful information, while medical texts generated by ChatGPT paid more attention to fluency and logic and usually expressed general terminologies rather than effective information specific to the context of the problem. A bidirectional encoder representations from transformers–based model effectively detected medical texts generated by ChatGPT, and the F1 score exceeded 95%. Conclusions: Although text generated by ChatGPT is grammatically perfect and human-like, the linguistic characteristics of generated medical texts were different from those written by human experts. Medical text generated by ChatGPT could be effectively detected by the proposed machine learning algorithms. This study provides a pathway toward trustworthy and accountable use of large language models in medicine.

13 September 2023
Verified
Book Chapter
Closed access
PDF file
HCHongmin Cai
Hongmin Cai
XHXiaoke Huang
Xiaoke Huang
ZLZhengliang Liu
Zhengliang Liu
WLWenxiong Liao
Wenxiong Liao
HDHaixing Dai
Haixing Dai
Xiang LiXiang Li
Xiang Li

20 March 2023 in arXiv
Verified
Preprint
Open access
PDF file
HDHaixing Dai
Haixing Dai
ZLZhengliang Liu
Zhengliang Liu
WLWenxiong Liao
Wenxiong Liao
XHXiaoke Huang
Xiaoke Huang
YCYihan Cao
Yihan Cao
XLXiang Li
Xiang Li
Text data augmentation is an effective strategy for overcoming the challenge of limited sample sizes in many natural language processing (NLP) tasks. This challenge is especially prominent in the few-shot learning scenario, where the data in the target domain is generally much scarcer and of lowered quality. A natural and widely-used strategy to mitigate such challenges is to perform data augmentation to better capture the data invariance and increase the sample size. However, current text data augmentation methods either can't ensure the correct labeling of the generated data (lacking faithfulness) or can't ensure sufficient diversity in the generated data (lacking compactness), or both. Inspired by the recent success of large language models, especially the development of ChatGPT, which demonstrated improved language comprehension abilities, in this work, we propose a text data augmentation approach based on ChatGPT (named AugGPT). AugGPT rephrases each sentence in the training samples into multiple conceptually similar but semantically different samples. The augmented samples can then be used in downstream model training. Experiment results on few-shot learning text classification tasks show the superior performance of the proposed AugGPT approach over state-of-the-art text data augmentation methods in terms of testing accuracy and distribution of the augmented samples.

19 May 2023 in JMIR Preprints
Verified
Preprint
Open access
WLWenxiong Liao
Wenxiong Liao
ZLZhengliang Liu
Zhengliang Liu
HDHaixing Dai
Haixing Dai
SXShaochen Xu
Shaochen Xu
ZWZihao Wu
Zihao Wu
Xiang LiXiang Li
Xiang Li
BACKGROUND Large language models, such as ChatGPT, are capable of generating grammatically perfect and human-like text content, and a large number of ChatGPT-generated texts have appeared on the internet. However, medical texts, such as clinical notes and diagnoses, require rigorous validation, and erroneous medical content generated by ChatGPT could potentially lead to disinformation that poses significant harm to health care and the general public. OBJECTIVE This study is among the first on responsible artificial intelligence–generated content in medicine. We focus on analyzing the differences between medical texts written by human experts and those generated by ChatGPT and designing machine learning workflows to effectively detect and differentiate medical texts generated by ChatGPT. METHODS We first constructed a suite of data sets containing medical texts written by human experts and generated by ChatGPT. We analyzed the linguistic features of these 2 types of content and uncovered differences in vocabulary, parts-of-speech, dependency, sentiment, perplexity, and other aspects. Finally, we designed and implemented machine learning methods to detect medical text generated by ChatGPT. The data and code used in this paper are published on GitHub. RESULTS Medical texts written by humans were more concrete, more diverse, and typically contained more useful information, while medical texts generated by ChatGPT paid more attention to fluency and logic and usually expressed general terminologies rather than effective information specific to the context of the problem. A bidirectional encoder representations from transformers–based model effectively detected medical texts generated by ChatGPT, and the F1 score exceeded 95%. CONCLUSIONS Although text generated by ChatGPT is grammatically perfect and human-like, the linguistic characteristics of generated medical texts were different from those written by human experts. Medical text generated by ChatGPT could be effectively detected by the proposed machine learning algorithms. This study provides a pathway toward trustworthy and accountable use of large language models in medicine.

27 September 2024 in Knowledge-Based Systems
Verified
Journal Article
Closed access
WLWenxiong Liao
Wenxiong Liao
ZLZhengliang Liu
Zhengliang Liu
YZYiyang Zhang
Yiyang Zhang
XHXiaoke Huang
Xiaoke Huang
NLNinghao Liu
Ninghao Liu
HCHongmin Cai
Hongmin Cai