Yuqing Wang

Yuqing Wang, Yun Zhao, Rachael Callcut et al. · stanford

Sepsis is a leading cause of death in the Intensive Care Units (ICU). Early detection of sepsis is critical for patient survival. In this paper, we propose a multimodal Transformer model for early sepsis prediction, using the physiological time series data and clinical notes for each patient within $36$ hours of ICU admission. Specifically, we aim to predict sepsis using only the first 12, 18, 24, 30 and 36 hours of laboratory measurements, vital signs, patient demographics, and clinical notes. We evaluate our model on two large critical care datasets: MIMIC-III and eICU-CRD. The proposed method is compared with six baselines. In addition, ablation analysis and case studies are conducted to study the influence of each individual component of the model and the contribution of each data modality for early sepsis prediction. Experimental results demonstrate the effectiveness of our method, which outperforms competitive baselines on all metrics.

Yuqing Wang, Yun Zhao, Linda Petzold · stanford

Large language models (LLMs) have made significant progress in various domains, including healthcare. However, the specialized nature of clinical language understanding tasks presents unique challenges and limitations that warrant further investigation. In this study, we conduct a comprehensive evaluation of state-of-the-art LLMs, namely GPT-3.5, GPT-4, and Bard, within the realm of clinical language understanding tasks. These tasks span a diverse range, including named entity recognition, relation extraction, natural language inference, semantic textual similarity, document classification, and question-answering. We also introduce a novel prompting strategy, self-questioning prompting (SQP), tailored to enhance LLMs' performance by eliciting informative questions and answers pertinent to the clinical scenarios at hand. Our evaluation underscores the significance of task-specific learning strategies and prompting techniques for improving LLMs' effectiveness in healthcare-related tasks. Additionally, our in-depth error analysis on the challenging relation extraction task offers valuable insights into error distribution and potential avenues for improvement using SQP. Our study sheds light on the practical implications of employing LLMs in the specialized domain of healthcare, serving as a foundation for future research and the development of potential applications in healthcare settings.

Yuqing Wang, Yun Zhao · stanford

In Large Language Models (LLMs), there have been consistent advancements in task-specific performance, largely influenced by effective prompt design. Recent advancements in prompting have enhanced reasoning in logic-intensive tasks for LLMs, yet the nuanced understanding abilities of these models, crucial for processing and interpreting complex information, remain underexplored. In this study, we introduce Metacognitive Prompting (MP), a strategy inspired by human introspective reasoning processes. Using MP, LLMs undergo a systematic series of structured, self-aware evaluations, drawing on both their vast inherent knowledge and new insights. We conduct extensive experiments on four prevalent LLMs: Llama2, PaLM2, GPT-3.5, and GPT-4, across ten natural language understanding (NLU) datasets from GLUE, SuperGLUE, BLUE, and LexGLUE benchmarks. Additionally, we compare our method with chain-of-thought prompting and its advanced versions. The results show that GPT-4 consistently excels across all tasks, while other models have shown significant progress in some tasks when used in conjunction with MP. Furthermore, MP consistently outperforms existing prompting methods in both general and domain-specific NLU tasks. This study underscores the potential to amplify the understanding abilities of LLMs and highlights the benefits of mirroring human introspective reasoning in NLU tasks.

Yuqing Wang, Yun Zhao · stanford

Reasoning about time is essential for understanding the nuances of events described in natural language. Previous research on this topic has been limited in scope, characterized by a lack of standardized benchmarks that would allow for consistent evaluations across different studies. In this paper, we introduce TRAM, a temporal reasoning benchmark composed of ten datasets, encompassing various temporal aspects of events such as order, arithmetic, frequency, and duration, designed to facilitate a comprehensive evaluation of the TeR capabilities of large language models (LLMs). We evaluate popular LLMs like GPT-4 and Llama2 in zero-shot and few-shot scenarios, and establish baselines with BERT-based and domain-specific models. Our findings indicate that the best-performing model lags significantly behind human performance. It is our aspiration that TRAM will spur further progress in enhancing the TeR capabilities of LLMs.

Yuqing Wang, Yun Zhao, Linda Petzold · stanford

Most current multivariate time series (MTS) classification algorithms focus on improving the predictive accuracy. However, for large-scale (either high-dimensional or long-sequential) time series (TS) datasets, there is an additional consideration: to design an efficient network architecture to reduce computational costs such as training time and memory footprint. In this work we propose a methodology based on module-wise pruning and Pareto analysis to investigate the relationship between model efficiency and accuracy, as well as its complexity. Comprehensive experiments on benchmark MTS datasets illustrate the effectiveness of our method.

Yuqing Wang, Yizhi Wang, Longhui Yu et al.

Vector font synthesis is a challenging and ongoing problem in the fields of Computer Vision and Computer Graphics. The recently-proposed DeepVecFont achieved state-of-the-art performance by exploiting information of both the image and sequence modalities of vector fonts. However, it has limited capability for handling long sequence data and heavily relies on an image-guided outline refinement post-processing. Thus, vector glyphs synthesized by DeepVecFont still often contain some distortions and artifacts and cannot rival human-designed results. To address the above problems, this paper proposes an enhanced version of DeepVecFont mainly by making the following three novel technical contributions. First, we adopt Transformers instead of RNNs to process sequential data and design a relaxation representation for vector outlines, markedly improving the model's capability and stability of synthesizing long and complex outlines. Second, we propose to sample auxiliary points in addition to control points to precisely align the generated and target Bézier curves or lines. Finally, to alleviate error accumulation in the sequential generation process, we develop a context-based self-refinement module based on another Transformer-based decoder to remove artifacts in the initially synthesized glyphs. Both qualitative and quantitative results demonstrate that the proposed method effectively resolves those intrinsic problems of the original DeepVecFont and outperforms existing approaches in generating English and Chinese vector fonts with complicated structures and diverse styles.

Haotian Xia, Zhengbang Yang, Junbo Zou et al.

Multimodal Large Language Models (MLLMs) are advancing the ability to reason about complex sports scenarios by integrating textual and visual information. To comprehensively evaluate their capabilities, we introduce SPORTU, a benchmark designed to assess MLLMs across multi-level sports reasoning tasks. SPORTU comprises two key components: SPORTU-text, featuring 900 multiple-choice questions with human-annotated explanations for rule comprehension and strategy understanding. This component focuses on testing models' ability to reason about sports solely through question-answering (QA), without requiring visual inputs; SPORTU-video, consisting of 1,701 slow-motion video clips across 7 different sports and 12,048 QA pairs, designed to assess multi-level reasoning, from simple sports recognition to complex tasks like foul detection and rule application. We evaluate four prevalent LLMs mainly utilizing few-shot learning paradigms supplemented by chain-of-thought (CoT) prompting on the SPORTU-text part. We evaluate four LLMs using few-shot learning and chain-of-thought (CoT) prompting on SPORTU-text. GPT-4o achieves the highest accuracy of 71%, but still falls short of human-level performance, highlighting room for improvement in rule comprehension and reasoning. The evaluation for the SPORTU-video part includes 7 proprietary and 6 open-source MLLMs. Experiments show that models fall short on hard tasks that require deep reasoning and rule-based understanding. Claude-3.5-Sonnet performs the best with only 52.6% accuracy on the hard task, showing large room for improvement. We hope that SPORTU will serve as a critical step toward evaluating models' capabilities in sports understanding and reasoning.

Yuqing Wang, Mika Mäntylä, Zihao Liu et al.

The popularity of continuous integration (CI) is increasing as a result of market pressure to release product features or updates frequently. The ability of CI to deliver quality at speed depends on reliable test automation. In this paper, we present an empirical study to observe the effect of test automation maturity (assessed by standard best practices in the literature) on product quality, test automation effort, and release cycle in the CI context of open source projects. We run our test automation maturity survey and got responses from 37 open source java projects. We also mined software repositories of the same projects. The main results of regression analysis reveal that, higher levels of test automation maturity are positively associated with higher product quality (p-value=0.000624) and shorter release cycle (p-value=0.01891); There is no statistically significant evidence of increased test automation effort due to higher levels of test automation maturity and product quality. Thus, we conclude that, a potential benefit of improving test automation maturity (using standard best practices) is product quality improvement and release cycle acceleration in the CI context of open source projects. We encourage future research to extend our findings by adding more datasets with different programming languages and CI tools, closed source projects, and large-scale industrial projects. Our recommendation to practitioners (in the similar CI context) is to utilize standard best practices to improve test automation maturity.

Yuqing Wang, Yun Zhao · stanford

The burgeoning interest in Multimodal Large Language Models (MLLMs), such as OpenAI's GPT-4V(ision), has significantly impacted both academic and industrial realms. These models enhance Large Language Models (LLMs) with advanced visual understanding capabilities, facilitating their application in a variety of multimodal tasks. Recently, Google introduced Gemini, a cutting-edge MLLM designed specifically for multimodal integration. Despite its advancements, preliminary benchmarks indicate that Gemini lags behind GPT models in commonsense reasoning tasks. However, this assessment, based on a limited dataset (i.e., HellaSWAG), does not fully capture Gemini's authentic commonsense reasoning potential. To address this gap, our study undertakes a thorough evaluation of Gemini's performance in complex reasoning tasks that necessitate the integration of commonsense knowledge across modalities. We carry out a comprehensive analysis of 12 commonsense reasoning datasets, ranging from general to domain-specific tasks. This includes 11 datasets focused solely on language, as well as one that incorporates multimodal elements. Our experiments across four LLMs and two MLLMs demonstrate Gemini's competitive commonsense reasoning capabilities. Additionally, we identify common challenges faced by current LLMs and MLLMs in addressing commonsense problems, underscoring the need for further advancements in enhancing the commonsense reasoning abilities of these models.

Haotian Xia, Zhengbang Yang, Yuqing Wang et al. · stanford

A deep understanding of sports, a field rich in strategic and dynamic content, is crucial for advancing Natural Language Processing (NLP). This holds particular significance in the context of evaluating and advancing Large Language Models (LLMs), given the existing gap in specialized benchmarks. To bridge this gap, we introduce SportQA, a novel benchmark specifically designed for evaluating LLMs in the context of sports understanding. SportQA encompasses over 70,000 multiple-choice questions across three distinct difficulty levels, each targeting different aspects of sports knowledge from basic historical facts to intricate, scenario-based reasoning tasks. We conducted a thorough evaluation of prevalent LLMs, mainly utilizing few-shot learning paradigms supplemented by chain-of-thought (CoT) prompting. Our results reveal that while LLMs exhibit competent performance in basic sports knowledge, they struggle with more complex, scenario-based sports reasoning, lagging behind human expertise. The introduction of SportQA marks a significant step forward in NLP, offering a tool for assessing and enhancing sports understanding in LLMs.

Yuqing Wang, Malvika Pillai, Yun Zhao et al. · stanford

In the high-stakes realm of healthcare, ensuring fairness in predictive models is crucial. Electronic Health Records (EHRs) have become integral to medical decision-making, yet existing methods for enhancing model fairness restrict themselves to unimodal data and fail to address the multifaceted social biases intertwined with demographic factors in EHRs. To mitigate these biases, we present FairEHR-CLP: a general framework for Fairness-aware Clinical Predictions with Contrastive Learning in EHRs. FairEHR-CLP operates through a two-stage process, utilizing patient demographics, longitudinal data, and clinical notes. First, synthetic counterparts are generated for each patient, allowing for diverse demographic identities while preserving essential health information. Second, fairness-aware predictions employ contrastive learning to align patient representations across sensitive attributes, jointly optimized with an MLP classifier with a softmax layer for clinical classification tasks. Acknowledging the unique challenges in EHRs, such as varying group sizes and class imbalance, we introduce a novel fairness metric to effectively measure error rate disparities across subgroups. Extensive experiments on three diverse EHR datasets on three tasks demonstrate the effectiveness of FairEHR-CLP in terms of fairness and utility compared with competitive baselines. FairEHR-CLP represents an advancement towards ensuring both accuracy and equity in predictive healthcare models.

Yuqing Wang, Xiao Yang · microsoft-research

Traditional security protection methods struggle to address sophisticated attack vectors in large-scale distributed systems, particularly when balancing detection accuracy with data privacy concerns. This paper presents a novel distributed security threat detection system that integrates federated learning with multimodal large language models (LLMs). Our system leverages federated learning to ensure data privacy while employing multimodal LLMs to process heterogeneous data sources including network traffic, system logs, images, and sensor data. Experimental evaluation on a 10TB distributed dataset demonstrates that our approach achieves 96.4% detection accuracy, outperforming traditional baseline models by 4.1 percentage points. The system reduces both false positive and false negative rates by 1.8 and 2.4 percentage points respectively. Performance analysis shows that our system maintains efficient processing capabilities in distributed environments, requiring 180 seconds for model training and 3.8 seconds for threat detection across the distributed network. These results demonstrate significant improvements in detection accuracy and computational efficiency while preserving data privacy, suggesting strong potential for real-world deployment in large-scale security systems.

Haotian Xia, Zhengbang Yang, Yun Zhao et al.

Recent integration of Natural Language Processing (NLP) and multimodal models has advanced the field of sports analytics. This survey presents a comprehensive review of the datasets and applications driving these innovations post-2020. We overviewed and categorized datasets into three primary types: language-based, multimodal, and convertible datasets. Language-based and multimodal datasets are for tasks involving text or multimodality (e.g., text, video, audio), respectively. Convertible datasets, initially single-modal (video), can be enriched with additional annotations, such as explanations of actions and video descriptions, to become multimodal, offering future potential for richer and more diverse applications. Our study highlights the contributions of these datasets to various applications, from improving fan experiences to supporting tactical analysis and medical diagnostics. We also discuss the challenges and future directions in dataset development, emphasizing the need for diverse, high-quality data to support real-time processing and personalized user experiences. This survey provides a foundational resource for researchers and practitioners aiming to leverage NLP and multimodal models in sports, offering insights into current trends and future opportunities in the field.

Longhui Yu, Zhenyu Weng, Yuqing Wang et al.

Incremental learning methods can learn new classes continually by distilling knowledge from the last model (as a teacher model) to the current model (as a student model) in the sequentially learning process. However, these methods cannot work for Incremental Implicitly-Refined Classification (IIRC), an incremental learning extension where the incoming classes could have two granularity levels, a superclass label and a subclass label. This is because the previously learned superclass knowledge may be occupied by the subclass knowledge learned sequentially. To solve this problem, we propose a novel Multi-Teacher Knowledge Distillation (MTKD) strategy. To preserve the subclass knowledge, we use the last model as a general teacher to distill the previous knowledge for the student model. To preserve the superclass knowledge, we use the initial model as a superclass teacher to distill the superclass knowledge as the initial model contains abundant superclass knowledge. However, distilling knowledge from two teacher models could result in the student model making some redundant predictions. We further propose a post-processing mechanism, called as Top-k prediction restriction to reduce the redundant predictions. Our experimental results on IIRC-ImageNet120 and IIRC-CIFAR100 show that the proposed method can achieve better classification accuracy compared with existing state-of-the-art methods.

Yuqing Wang, Minshuo Chen, Tuo Zhao et al.

Recent empirical advances show that training deep models with large learning rate often improves generalization performance. However, theoretical justifications on the benefits of large learning rate are highly limited, due to challenges in analysis. In this paper, we consider using Gradient Descent (GD) with a large learning rate on a homogeneous matrix factorization problem, i.e., $\min_{X, Y} \|A - XY^\top\|_{\sf F}^2$. We prove a convergence theory for constant large learning rates well beyond $2/L$, where $L$ is the largest eigenvalue of Hessian at the initialization. Moreover, we rigorously establish an implicit bias of GD induced by such a large learning rate, termed 'balancing', meaning that magnitudes of $X$ and $Y$ at the limit of GD iterations will be close even if their initialization is significantly unbalanced. Numerical experiments are provided to support our theory.

Yun Zhao, Qinghang Hong, Xinlu Zhang et al.

Survival analysis is a technique to predict the times of specific outcomes, and is widely used in predicting the outcomes for intensive care unit (ICU) trauma patients. Recently, deep learning models have drawn increasing attention in healthcare. However, there is a lack of deep learning methods that can model the relationship between measurements, clinical notes and mortality outcomes. In this paper we introduce BERTSurv, a deep learning survival framework which applies Bidirectional Encoder Representations from Transformers (BERT) as a language representation model on unstructured clinical notes, for mortality prediction and survival analysis. We also incorporate clinical measurements in BERTSurv. With binary cross-entropy (BCE) loss, BERTSurv can predict mortality as a binary outcome (mortality prediction). With partial log-likelihood (PLL) loss, BERTSurv predicts the probability of mortality as a time-to-event outcome (survival analysis). We apply BERTSurv on Medical Information Mart for Intensive Care III (MIMIC III) trauma patient data. For mortality prediction, BERTSurv obtained an area under the curve of receiver operating characteristic curve (AUC-ROC) of 0.86, which is an improvement of 3.6% over baseline of multilayer perceptron (MLP) without notes. For survival analysis, BERTSurv achieved a concordance index (C-index) of 0.7. In addition, visualizations of BERT's attention heads help to extract patterns in clinical notes and improve model interpretability by showing how the model assigns weights to different inputs.

Kaixuan Huang, Yuqing Wang, Molei Tao et al.

Deep residual networks (ResNets) have demonstrated better generalization performance than deep feedforward networks (FFNets). However, the theory behind such a phenomenon is still largely unknown. This paper studies this fundamental problem in deep learning from a so-called "neural tangent kernel" perspective. Specifically, we first show that under proper conditions, as the width goes to infinity, training deep ResNets can be viewed as learning reproducing kernel functions with some kernel function. We then compare the kernel of deep ResNets with that of deep FFNets and discover that the class of functions induced by the kernel of FFNets is asymptotically not learnable, as the depth goes to infinity. In contrast, the class of functions induced by the kernel of ResNets does not exhibit such degeneracy. Our discovery partially justifies the advantages of deep ResNets over deep FFNets in generalization abilities. Numerical results are provided to support our claim.