Peiyang Yu

Dr. Peiyang Yu

orcid

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

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

Representative Publications

View All Publications

3 February 2025 in Preprints.org
Verified
Preprint
Open access
PDF file
JYJingyuan Yi
Jingyuan Yi
ZXZeqiu Xu
Zeqiu Xu
THTianyi Huang
Tianyi Huang
PYPeiyang Yu
Peiyang Yu
The pervasiveness of the dissemination of fake news through social media platforms poses critical risks to the trust of the general public, societal stability, and democratic institutions. This challenge calls for novel methodologies in detection, which can keep pace with the dynamic and multi-modal nature of misinformation. Recent works include powering the detection using large language model advances in multimodal frameworks, methodologies using graphs, and adversarial training in the literature of fake news. Based on the different approaches which can bring success, some key highlights will be underlined: enhanced LLM-improves accuracy through more advanced semantics and cross-modality fusion for robust detections. The review further identifies critical gaps in adaptability to dynamic social media trends, real-time, and cross-platform detection capabilities. Future directions underline the development of style-agnostic models, cross-lingual detection frameworks, and robust policies with a view to mitigating LLM-driven misinformation. This synthesis thus lays a concrete foundation for those researchers and practitioners committed to reinforcing fake news detection systems with complications that keep on growing in the digital landscape.

8 January 2025 in Preprints.org
Verified
Preprint
Open access
PDF file
XXXiaochuan Xu
Xiaochuan Xu
ZXZeqiu Xu
Zeqiu Xu
PYPeiyang Yu
Peiyang Yu
JWJiani Wang
Jiani Wang
Recommendation systems play a critical role in enhancing user experience and engagement in various online platforms. Traditional methods, such as Collaborative Filtering (CF) and Content-Based Filtering (CBF), rely heavily on past user interactions or item features. However, these models often fail to capture the dynamic and evolving nature of user preferences. To address these limitations, we propose DUIP (Dynamic User Intent Prediction), a novel framework that combines LSTM networks with Large Language Models (LLMs) to dynam- ically capture user intent and generate personalized item recommendations. The LSTM component models the sequential and temporal dependencies of user behavior, while the LLM utilizes the LSTM-generated prompts to predict the next item of interest. Experimental results on three diverse datasets—ML-1M, Games, and Bun- dle—show that DUIP outperforms a wide range of baseline models, demonstrating its ability to handle the cold-start problem and real-time intent adaptation. The integration of dynamic prompts based on recent user interactions allows DUIP to provide more accurate, context-aware, and personalized recommendations. Our findings suggest that DUIP is a promising approach for next-generation recommendation systems, with potential for further improvements in cross-modal recommendations and scalability.

2 March 2025 in arXiv
Verified
Preprint
Open access
PDF file
THTianyi Huang
Tianyi Huang
JYJingyuan Yi
Jingyuan Yi
PYPeiyang Yu
Peiyang Yu
XXXiaochuan Xu
Xiaochuan Xu
The proliferation of misinformation on social media has raised significant societal concerns, necessitating robust detection mechanisms. Large Language Models such as GPT-4 and LLaMA2 have been envisioned as possible tools for detecting misinformation based on their advanced natural language understanding and reasoning capabilities. This paper conducts a comparison of LLM-based approaches to detecting misinformation between text-based, multimodal, and agentic approaches. We evaluate the effectiveness of fine-tuned models, zero-shot learning, and systematic fact-checking mechanisms in detecting misinformation across different topic domains like public health, politics, and finance. We also discuss scalability, generalizability, and explainability of the models and recognize key challenges such as hallucination, adversarial attacks on misinformation, and computational resources. Our findings point towards the importance of hybrid approaches that pair structured verification protocols with adaptive learning techniques to enhance detection accuracy and explainability. The paper closes by suggesting potential avenues of future work, including real-time tracking of misinformation, federated learning, and cross-platform detection models.

27 March 2025 in Preprints.org
Verified
Preprint
Open access
PDF file
ZXZeqiu Xu
Zeqiu Xu
JWJiani Wang
Jiani Wang
XXXiaochuan Xu
Xiaochuan Xu
PYPeiyang Yu
Peiyang Yu
THTianyi Huang
Tianyi Huang
JYJingyuan Yi
Jingyuan Yi
As deep learning models are widely applied across various domains, a critical challenge is how to compress models while maintaining high reasoning capability. Knowledge distillation, an effective technique for model compression, has been used to enhance the performance of lightweight models. However, traditional distillation methods are limited when dealing with complex reasoning tasks. Reinforcement learning (RL) offers a novel approach to knowledge distillation by optimizing the reasoning strategies of teacher models, generating more efficient decision paths, and providing more valuable learning content for student models. This paper reviews the latest advancements in combining reinforcement learning with knowledge distillation, focusing on policy distillation, value function distillation, and dynamic reward-guided distillation methods. It also discusses the challenges faced by RL-driven distillation, such as simplifying complex strategies, addressing temporal dependencies, and balancing exploration and exploitation, and suggests possible solutions. Finally, this paper explores the applications of RL-driven knowledge distillation in fields such as game AI, robotic control, and dialogue systems, and outlines future research directions, including automated distillation, multimodal distillation, and challenges in federated learning.

11 March 2025 in arXiv
Verified
Preprint
Open access
PDF file
JYJingyuan Yi
Jingyuan Yi
PYPeiyang Yu
Peiyang Yu
THTianyi Huang
Tianyi Huang
XXXiaochuan Xu
Xiaochuan Xu
This work proposes an LSTM-based sentiment classification model with multi-head attention mechanism and TF-IDF optimization. Through the integration of TF-IDF feature extraction and multi-head attention, the model significantly improves text sentiment analysis performance. Experimental results on public data sets demonstrate that the new method achieves substantial improvements in the most critical metrics like accuracy, recall, and F1-score compared to baseline models. Specifically, the model achieves an accuracy of 80.28% on the test set, which is improved by about 12% in comparison with standard LSTM models. Ablation experiments also support the necessity and necessity of all modules, in which the impact of multi-head attention is greatest to performance improvement. This research provides a proper approach to sentiment analysis, which can be utilized in public opinion monitoring, product recommendation, etc.