arXiv subjects

Xishuang Dong

Publications and source records attributed to Xishuang Dong.

At least 19 recordsLinked to original sources

arXiv2026

UA-ChatDev: Uncertainty-Aware Multi-Agent Collaboration for Reliable Software Development

Software development is a complex task that demands cooperation among agents with diverse roles. Large language models (LLMs) have enabled autonomous multi-agent software development frameworks that leverage role-based collaboration to automate requirements analysis, coding, testing, and refinement. However, existing approaches typically assume that intermediate agent outputs are equally reliable, leaving them vulnerable to hallucination propagation, where incorrect decisions generated in early development phases are transferred to downstream agents and negatively impact final software quality. To address this challenge, we propose UA-ChatDev, an uncertainty-aware multi-agent software development framework that integrates uncertainty quantification into agent interactions. It introduces a lightweight uncertainty estimation mechanism based on token-level log probabilities to assess the confidence of agent responses and employs phase-aware threshold calibration to selectively trigger retrieval-based verification when uncertainty exceeds acceptable levels. Extensive experiments on the SRDD benchmark demonstrate that UA-ChatDev consistently outperforms existing single-agent and multi-agent software development frameworks across completeness, executability, consistency, and overall quality metrics. Further ablation studies and communication analyses verify that uncertainty-aware interactions enhance code execution reliability.

cs.AI↗

arXiv2025

Multi-task GINN-LP for Multi-target Symbolic Regression

In the area of explainable artificial intelligence, Symbolic Regression (SR) has emerged as a promising approach by discovering interpretable mathematical expressions that fit data. However, SR faces two main challenges: most methods are evaluated on scientific datasets with well-understood relationships, limiting generalization, and SR primarily targets single-output regression, whereas many real-world problems involve multi-target outputs with interdependent variables. To address these issues, we propose multi-task regression GINN-LP (MTRGINN-LP), an interpretable neural network for multi-target symbolic regression. By integrating GINN-LP with a multi-task deep learning, the model combines a shared backbone including multiple power-term approximator blocks with task-specific output layers, capturing inter-target dependencies while preserving interpretability. We validate multi-task GINN-LP on practical multi-target applications, including energy efficiency prediction and sustainable agriculture. Experimental results demonstrate competitive predictive performance alongside high interpretability, effectively extending symbolic regression to broader real-world multi-output tasks.

cs.LG↗

arXiv2025

Systematic Comparative Analysis of Large Pretrained Language Models on Contextualized Medication Event Extraction

Attention-based models have become the leading approach in modeling medical language for Natural Language Processing (NLP) in clinical notes. These models outperform traditional techniques by effectively capturing contextual representations of language. In this research a comparative analysis is done amongst pre-trained attention based models namely Bert Base, BioBert, two variations of Bio+Clinical Bert, RoBerta, and Clinical Longformer on task related to Electronic Health Record (EHR) information extraction. The tasks from Track 1 of Harvard Medical School's 2022 National Clinical NLP Challenges (n2c2) are considered for this comparison, with the Contextualized Medication Event Dataset (CMED) given for these task. CMED is a dataset of unstructured EHRs and annotated notes that contain task relevant information about the EHRs. The goal of the challenge is to develop effective solutions for extracting contextual information related to patient medication events from EHRs using data driven methods. Each pre-trained model is fine-tuned and applied on CMED to perform medication extraction, medical event detection, and multi-dimensional medication event context classification. Processing methods are also detailed for breaking down EHRs for compatibility with the applied models. Performance analysis has been carried out using a script based on constructing medical terms from the evaluation portion of CMED with metrics including recall, precision, and F1-Score. The results demonstrate that models pre-trained on clinical data are more effective in detecting medication and medication events, but Bert Base, pre-trained on general domain data showed to be the most effective for classifying the context of events related to medications.

cs.CL↗

arXiv2025

Enhancing Learning Path Recommendation via Multi-task Learning

Personalized learning is a student-centered educational approach that adapts content, pace, and assessment to meet each learner's unique needs. As the key technique to implement the personalized learning, learning path recommendation sequentially recommends personalized learning items such as lectures and exercises. Advances in deep learning, particularly deep reinforcement learning, have made modeling such recommendations more practical and effective. This paper proposes a multi-task LSTM model that enhances learning path recommendation by leveraging shared information across tasks. The approach reframes learning path recommendation as a sequence-to-sequence (Seq2Seq) prediction problem, generating personalized learning paths from a learner's historical interactions. The model uses a shared LSTM layer to capture common features for both learning path recommendation and deep knowledge tracing, along with task-specific LSTM layers for each objective. To avoid redundant recommendations, a non-repeat loss penalizes repeated items within the recommended learning path. Experiments on the ASSIST09 dataset show that the proposed model significantly outperforms baseline methods for the learning path recommendation.

cs.IR↗

arXiv2025

Ensemble BERT for Medication Event Classification on Electronic Health Records (EHRs)

Identification of key variables such as medications, diseases, relations from health records and clinical notes has a wide range of applications in the clinical domain. n2c2 2022 provided shared tasks on challenges in natural language processing for clinical data analytics on electronic health records (EHR), where it built a comprehensive annotated clinical data Contextualized Medication Event Dataset (CMED). This study focuses on subtask 2 in Track 1 of this challenge that is to detect and classify medication events from clinical notes through building a novel BERT-based ensemble model. It started with pretraining BERT models on different types of big data such as Wikipedia and MIMIC. Afterwards, these pretrained BERT models were fine-tuned on CMED training data. These fine-tuned BERT models were employed to accomplish medication event classification on CMED testing data with multiple predictions. These multiple predictions generated by these fine-tuned BERT models were integrated to build final prediction with voting strategies. Experimental results demonstrated that BERT-based ensemble models can effectively improve strict Micro-F score by about 5% and strict Macro-F score by about 6%, respectively.

cs.CL↗

arXiv2025

Knowledge Acquisition on Mass-shooting Events via LLMs for AI-Driven Justice

Mass-shooting events pose a significant challenge to public safety, generating large volumes of unstructured textual data that hinder effective investigations and the formulation of public policy. Despite the urgency, few prior studies have effectively automated the extraction of key information from these events to support legal and investigative efforts. This paper presented the first dataset designed for knowledge acquisition on mass-shooting events through the application of named entity recognition (NER) techniques. It focuses on identifying key entities such as offenders, victims, locations, and criminal instruments, that are vital for legal and investigative purposes. The NER process is powered by Large Language Models (LLMs) using few-shot prompting, facilitating the efficient extraction and organization of critical information from diverse sources, including news articles, police reports, and social media. Experimental results on real-world mass-shooting corpora demonstrate that GPT-4o is the most effective model for mass-shooting NER, achieving the highest Micro Precision, Micro Recall, and Micro F1-scores. Meanwhile, o1-mini delivers competitive performance, making it a resource-efficient alternative for less complex NER tasks. It is also observed that increasing the shot count enhances the performance of all models, but the gains are more substantial for GPT-4o and o1-mini, highlighting their superior adaptability to few-shot learning scenarios.

cs.CY↗

arXiv2024

Data Augmentation via Diffusion Model to Enhance AI Fairness

AI fairness seeks to improve the transparency and explainability of AI systems by ensuring that their outcomes genuinely reflect the best interests of users. Data augmentation, which involves generating synthetic data from existing datasets, has gained significant attention as a solution to data scarcity. In particular, diffusion models have become a powerful technique for generating synthetic data, especially in fields like computer vision. This paper explores the potential of diffusion models to generate synthetic tabular data to improve AI fairness. The Tabular Denoising Diffusion Probabilistic Model (Tab-DDPM), a diffusion model adaptable to any tabular dataset and capable of handling various feature types, was utilized with different amounts of generated data for data augmentation. Additionally, reweighting samples from AIF360 was employed to further enhance AI fairness. Five traditional machine learning models-Decision Tree (DT), Gaussian Naive Bayes (GNB), K-Nearest Neighbors (KNN), Logistic Regression (LR), and Random Forest (RF)-were used to validate the proposed approach. Experimental results demonstrate that the synthetic data generated by Tab-DDPM improves fairness in binary classification.

cs.LG↗

arXiv2024

Enhancing LLM Fine-tuning for Text-to-SQLs by SQL Quality Measurement

Text-to-SQLs enables non-expert users to effortlessly retrieve desired information from relational databases using natural language queries. While recent advancements, particularly with Large Language Models (LLMs) like GPT and T5, have shown impressive performance on large-scale benchmarks such as BIRD, current state-of-the-art (SOTA) LLM-based Text-to-SQLs models often require significant efforts to develop auxiliary tools like SQL classifiers to achieve high performance. This paper proposed a novel approach that only needs SQL Quality Measurement to enhance LLMs-based Text-to-SQLs performance. It establishes a SQL quality evaluation mechanism to assess the generated SQL queries against predefined criteria and actual database responses. This feedback loop enables continuous learning and refinement of model outputs based on both syntactic correctness and semantic accuracy. The proposed method undergoes comprehensive validation on the BIRD benchmark, assessing Execution Accuracy (EX) and Valid Efficiency Score (VES) across various Text-to-SQLs difficulty levels. Experimental results reveal competitive performance in both EX and VES compared to SOTA models like GPT4 and T5.

cs.DB↗

arXiv2024

Deep Knowledge Tracing for Personalized Adaptive Learning at Historically Black Colleges and Universities

Personalized adaptive learning (PAL) stands out by closely monitoring individual students' progress and tailoring their learning paths to their unique knowledge and needs. A crucial technique for effective PAL implementation is knowledge tracing, which models students' evolving knowledge to predict their future performance. Recent advancements in deep learning have significantly enhanced knowledge tracing through Deep Knowledge Tracing (DKT). However, there is limited research on DKT for Science, Technology, Engineering, and Math (STEM) education at Historically Black Colleges and Universities (HBCUs). This study builds a comprehensive dataset to investigate DKT for implementing PAL in STEM education at HBCUs, utilizing multiple state-of-the-art (SOTA) DKT models to examine knowledge tracing performance. The dataset includes 352,148 learning records for 17,181 undergraduate students across eight colleges at Prairie View A&M University (PVAMU). The SOTA DKT models employed include DKT, DKT+, DKVMN, SAKT, and KQN. Experimental results demonstrate the effectiveness of DKT models in accurately predicting students' academic outcomes. Specifically, the SAKT and KQN models outperform others in terms of accuracy and AUC. These findings have significant implications for faculty members and academic advisors, providing valuable insights for identifying students at risk of academic underperformance before the end of the semester. Furthermore, this allows for proactive interventions to support students' academic progress, potentially enhancing student retention and graduation rates.

cs.CY↗

arXiv2024

Enhancing Deep Knowledge Tracing via Diffusion Models for Personalized Adaptive Learning

In contrast to pedagogies like evidence-based teaching, personalized adaptive learning (PAL) distinguishes itself by closely monitoring the progress of individual students and tailoring the learning path to their unique knowledge and requirements. A crucial technique for effective PAL implementation is knowledge tracing, which models students' evolving knowledge to predict their future performance. Based on these predictions, personalized recommendations for resources and learning paths can be made to meet individual needs. Recent advancements in deep learning have successfully enhanced knowledge tracking through Deep Knowledge Tracing (DKT). This paper introduces generative AI models to further enhance DKT. Generative AI models, rooted in deep learning, are trained to generate synthetic data, addressing data scarcity challenges in various applications across fields such as natural language processing (NLP) and computer vision (CV). This study aims to tackle data shortage issues in student learning records to enhance DKT performance for PAL. Specifically, it employs TabDDPM, a diffusion model, to generate synthetic educational records to augment training data for enhancing DKT. The proposed method's effectiveness is validated through extensive experiments on ASSISTments datasets. The experimental results demonstrate that the AI-generated data by TabDDPM significantly improves DKT performance, particularly in scenarios with small data for training and large data for testing.

cs.CY↗

arXiv2023

Comprehensive Validation on Reweighting Samples for Bias Mitigation via AIF360

Fairness AI aims to detect and alleviate bias across the entire AI development life cycle, encompassing data curation, modeling, evaluation, and deployment-a pivotal aspect of ethical AI implementation. Addressing data bias, particularly concerning sensitive attributes like gender and race, reweighting samples proves efficient for fairness AI. This paper contributes a systematic examination of reweighting samples for traditional machine learning (ML) models, employing five models for binary classification on the Adult Income and COMPUS datasets with various protected attributes. The study evaluates prediction results using five fairness metrics, uncovering the nuanced and model-specific nature of reweighting sample effectiveness in achieving fairness in traditional ML models, as well as revealing the complexity of bias dynamics.

cs.LG↗

arXiv2023

Medical Data Augmentation via ChatGPT: A Case Study on Medication Identification and Medication Event Classification

The identification of key factors such as medications, diseases, and relationships within electronic health records and clinical notes has a wide range of applications in the clinical field. In the N2C2 2022 competitions, various tasks were presented to promote the identification of key factors in electronic health records (EHRs) using the Contextualized Medication Event Dataset (CMED). Pretrained large language models (LLMs) demonstrated exceptional performance in these tasks. This study aims to explore the utilization of LLMs, specifically ChatGPT, for data augmentation to overcome the limited availability of annotated data for identifying the key factors in EHRs. Additionally, different pre-trained BERT models, initially trained on extensive datasets like Wikipedia and MIMIC, were employed to develop models for identifying these key variables in EHRs through fine-tuning on augmented datasets. The experimental results of two EHR analysis tasks, namely medication identification and medication event classification, indicate that data augmentation based on ChatGPT proves beneficial in improving performance for both medication identification and medication event classification.

cs.CL↗

arXiv2022

Calibrated Bagging Deep Learning for Image Semantic Segmentation: A Case Study on COVID-19 Chest X-ray Image

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) causes coronavirus disease 2019 (COVID-19). Imaging tests such as chest X-ray (CXR) and computed tomography (CT) can provide useful information to clinical staff for facilitating a diagnosis of COVID-19 in a more efficient and comprehensive manner. As a breakthrough of artificial intelligence (AI), deep learning has been applied to perform COVID-19 infection region segmentation and disease classification by analyzing CXR and CT data. However, prediction uncertainty of deep learning models for these tasks, which is very important to safety-critical applications like medical image processing, has not been comprehensively investigated. In this work, we propose a novel ensemble deep learning model through integrating bagging deep learning and model calibration to not only enhance segmentation performance, but also reduce prediction uncertainty. The proposed method has been validated on a large dataset that is associated with CXR image segmentation. Experimental results demonstrate that the proposed method can improve the segmentation performance, as well as decrease prediction uncertainties.

eess.IV↗

arXiv2022

Integrating Human-in-the-loop into Swarm Learning for Decentralized Fake News Detection

Social media has become an effective platform to generate and spread fake news that can mislead people and even distort public opinion. Centralized methods for fake news detection, however, cannot effectively protect user privacy during the process of centralized data collection for training models. Moreover, it cannot fully involve user feedback in the loop of learning detection models for further enhancing fake news detection. To overcome these challenges, this paper proposed a novel decentralized method, Human-in-the-loop Based Swarm Learning (HBSL), to integrate user feedback into the loop of learning and inference for recognizing fake news without violating user privacy in a decentralized manner. It consists of distributed nodes that are able to independently learn and detect fake news on local data. Furthermore, detection models trained on these nodes can be enhanced through decentralized model merging. Experimental results demonstrate that the proposed method outperforms the state-of-the-art decentralized method in regard of detecting fake news on a benchmark dataset.

cs.LG↗

arXiv2021

Efficient Privacy Preserving Edge Computing Framework for Image Classification

In order to extract knowledge from the large data collected by edge devices, traditional cloud based approach that requires data upload may not be feasible due to communication bandwidth limitation as well as privacy and security concerns of end users. To address these challenges, a novel privacy preserving edge computing framework is proposed in this paper for image classification. Specifically, autoencoder will be trained unsupervised at each edge device individually, then the obtained latent vectors will be transmitted to the edge server for the training of a classifier. This framework would reduce the communications overhead and protect the data of the end users. Comparing to federated learning, the training of the classifier in the proposed framework does not subject to the constraints of the edge devices, and the autoencoder can be trained independently at each edge device without any server involvement. Furthermore, the privacy of the end users' data is protected by transmitting latent vectors without additional cost of encryption. Experimental results provide insights on the image classification performance vs. various design parameters such as the data compression ratio of the autoencoder and the model complexity.

cs.LG↗

arXiv2021

A Novel Dataset for Keypoint Detection of quadruped Animals from Images

In this paper, we studied the problem of localizing a generic set of keypoints across multiple quadruped or four-legged animal species from images. Due to the lack of large scale animal keypoint dataset with ground truth annotations, we developed a novel dataset, AwA Pose, for keypoint detection of quadruped animals from images. Our dataset contains significantly more keypoints per animal and has much more diverse animals than the existing datasets for animal keypoint detection. We benchmarked the dataset with a state-of-the-art deep learning model for different keypoint detection tasks, including both seen and unseen animal cases. Experimental results showed the effectiveness of the dataset. We believe that this dataset will help the computer vision community in the design and evaluation of improved models for the generalized quadruped animal keypoint detection problem.

cs.CV↗

arXiv2021

Semi-supervised Learning for COVID-19 Image Classification via ResNet

Coronavirus disease 2019 (COVID-19) is an ongoing global pandemic in over 200 countries and territories, which has resulted in a great public health concern across the international community. Analysis of X-ray imaging data can play a critical role in timely and accurate screening and fighting against COVID-19. Supervised deep learning has been successfully applied to recognize COVID-19 pathology from X-ray imaging datasets. However, it requires a substantial amount of annotated X-ray images to train models, which is often not applicable to data analysis for emerging events such as COVID-19 outbreak, especially in the early stage of the outbreak. To address this challenge, this paper proposes a two-path semi-supervised deep learning model, ssResNet, based on Residual Neural Network (ResNet) for COVID-19 image classification, where two paths refer to a supervised path and an unsupervised path, respectively. Moreover, we design a weighted supervised loss that assigns higher weight for the minority classes in the training process to resolve the data imbalance. Experimental results on a large-scale of X-ray image dataset COVIDx demonstrate that the proposed model can achieve promising performance even when trained on very few labeled training images.

eess.IV↗

arXiv2020

Cell Type Identification from Single-Cell Transcriptomic Data via Semi-supervised Learning

Cell type identification from single-cell transcriptomic data is a common goal of single-cell RNA sequencing (scRNAseq) data analysis. Neural networks have been employed to identify cell types from scRNAseq data with high performance. However, it requires a large mount of individual cells with accurate and unbiased annotated types to build the identification models. Unfortunately, labeling the scRNAseq data is cumbersome and time-consuming as it involves manual inspection of marker genes. To overcome this challenge, we propose a semi-supervised learning model to use unlabeled scRNAseq cells and limited amount of labeled scRNAseq cells to implement cell identification. Firstly, we transform the scRNAseq cells to "gene sentences", which is inspired by similarities between natural language system and gene system. Then genes in these sentences are represented as gene embeddings to reduce data sparsity. With these embeddings, we implement a semi-supervised learning model based on recurrent convolutional neural networks (RCNN), which includes a shared network, a supervised network and an unsupervised network. The proposed model is evaluated on macosko2015, a large scale single-cell transcriptomic dataset with ground truth of individual cell types. It is observed that the proposed model is able to achieve encouraging performance by learning on very limited amount of labeled scRNAseq cells together with a large number of unlabeled scRNAseq cells.

q-bio.GN↗