Wei Xu’s research while affiliated with Renmin University of China and other places

Text style transfer plays a vital role in online entertainment and social media. However, existing models struggle to handle the complexity of Chinese long texts, such as rhetoric, structure, and culture, which restricts their broader application. To bridge this gap, we propose a C hinese A rticle-style T ransfer ( CAT-LLM ) framework, which addresses the challenges of style transfer in complex Chinese long texts. At its core, CAT-LLM features a bespoke pluggable T ext S tyle D efinition ( TSD ) module that integrates machine learning algorithms to analyze and model article styles at both word and sentence levels. This module acts as a bridge, enabling large language models (LLMs) to better understand and adapt to the complexities of Chinese article styles. Furthermore, it supports the dynamic expansion of internal style trees, enabling the framework to seamlessly incorporate new and diverse style definitions, enhancing adaptability and scalability for future research and applications. Additionally, to facilitate robust evaluation, we created ten parallel datasets using a combination of ChatGPT and various Chinese texts, each corresponding to distinct writing styles, significantly improving the accuracy of the model evaluation and establishing a novel paradigm for text style transfer research. Extensive experimental results demonstrate that CAT-LLM, combined with GPT-3.5-Turbo, achieves state-of-the-art performance, with a transfer accuracy F1 score of 79.36% and a content preservation F1 score of 96.47% on the “Fortress Besieged” dataset. These results highlight CAT-LLM's innovative contributions to style transfer research, including its ability to preserve content integrity while achieving precise and flexible style transfer across diverse Chinese text domains. Building on these contributions, CAT-LLM presents significant potential for advancing Chinese digital media and facilitating automated content creation. Source code is available at GitHub ¹ .

Crime detection is crucial for creating and sustaining peaceful societies. In this study, we introduce Internet of Things (IoT) technology into the development of crime detection systems. Utilizing the situational crime prevention (SCP) theory from criminology, we propose a feature engineering method to extract IoT-based features that describe, explain, and predict criminal activities. In addition to commonly used features in traditional crime detection, we derive four groups of features based on SCP: criminal efforts, criminal risks, anticipated rewards, and excuses. In addition, to address growing concerns about IoT privacy issues, we incorporate a data synthesizer into our framework to generate privacy-preserving data similar to the original, allowing predictive models to be trained without accessing private information. The synthesizer uses a Bayesian network model combined with differential privacy techniques through the Laplace mechanism. Our results, based on real-world data sets, demonstrate that the proposed IoT-enabled crime detection system can achieve high-performance crime detection and has the potential to increase border surveillance efficiency with limited police resources. Our study highlights the power of artificial intelligence (AI) analytics and provides a viable framework solution for the responsible development of AI-based systems. History: This paper has been accepted by Kaushik Dutta for the Special Issue on the Responsible AI and Data Science for Social Good. Supplemental Material: The software that supports the findings of this study is available within the paper and its Supplemental Information ( https://pubsonline.informs.org/doi/suppl/10.1287/ijoc.2023.0488 ) as well as from the IJOC GitHub software repository ( https://github.com/INFORMSJoC/2023.0488 ). The complete IJOC Software and Data Repository is available at https://informsjoc.github.io/ .

The goal of this repository is to demonstrate our proposed design framework for responsible AI systems that support proactive crime detection and real-time response.

The beauty industry has experienced concurrent growth alongside an increased societal emphasis on aesthetics. The advent of digital platforms has not only propelled the expansion of the cosmetic sector but has also provided an avenue for in-depth scrutiny of cosmetic services. Digital platforms dedicated to discussing and analyzing cosmetic procedures offer unprecedented opportunities for researchers to examine service dynamics. This study explores the impact of information embedded in images on digital platforms on business performance in the cosmetic industry. Employing a deep learning framework, we extract beauty information from post-treatment images shared by consumers and scrutinize its relationship with the performance of cosmetic services. Drawing on data from an online-to-offline cosmetic platform, our empirical findings reveal a positive association between beauty information and the performance of cosmetic services. Furthermore, we identify service variety and service risk as moderating factors that influence the correlation between beauty information and performance on digital cosmetic platforms. The outcomes of this research carry significant implications for the beauty industry and stakeholders in digital cosmetic platforms.

Large language models (LLMs) have transformed human writing by enhancing grammar correction, content expansion, and stylistic refinement. However, their widespread use raises concerns about authorship, originality, and ethics, even potentially threatening scholarly integrity. Existing detection methods, which mainly rely on single-feature analysis and binary classification, often fail to effectively identify LLM-generated text in academic contexts. To address these challenges, we propose a novel Multi-level Fine-grained Detection (MFD) framework that detects LLM-generated text by integrating low-level structural, high-level semantic, and deep-level linguistic features, while conducting sentence-level evaluations of lexicon, grammar, and syntax for comprehensive analysis. To improve detection of subtle differences in LLM-generated text and enhance robustness against paraphrasing, we apply two mainstream evasion techniques to rewrite the text. These variations, along with original texts, are used to train a text encoder via contrastive learning, extracting high-level semantic features of sentence to boost detection generalization. Furthermore, we leverage advanced LLM to analyze the entire text and extract deep-level linguistic features, enhancing the model's ability to capture complex patterns and nuances while effectively incorporating contextual information. Extensive experiments on public datasets show that the MFD model outperforms existing methods, achieving an MAE of 0.1346 and an accuracy of 88.56%. Our research provides institutions and publishers with an effective mechanism to detect LLM-generated text, mitigating risks of compromised authorship. Educators and editors can use the model's predictions to refine verification and plagiarism prevention protocols, ensuring adherence to standards.

Accurately predicting investment returns is one of the most widely investigated and challenging problems for investors and researchers. In this paper, we propose a Return-to-Return (R2R) mathematical approach for capturing return movements by simplifying feature-driven barriers and focusing only on daily return rate. In the R2R framework, we devise a security alignment technique and derive the Expected Alignment Deviation (EAD)-based predicting functions by considering the synchronous evolution of daily return deviations. The EAD matrix for all security in the portfolio serves as the foundation for the grouping method used to identify Key Security Leaders (KSLs) and predict security returns. Subsequently, we propose mean–variance portfolio optimization models that incorporate KSLs from each group. These models are transformed into two forms: continuous period and discrete period. Finally, we validate the effectiveness of our method through an experimental analysis of Chinese stocks.