Computer Sciences Commons^™

Synthesis And Evaluation Of Long-Term History-Aware Medical Dialogue, Hebin Hu, Renke Dai, Ah-Hwee Tan, Yilin Kang

Research Collection School Of Computing and Information Systems

An effective healthcare agent must be able to recall and reason over a patient’s longitudinal medical history. However, the absence of datasets with realistic long-term dialogue timelines limits systematic evaluation. Real clinical text is constrained by privacy and ethics, while existing benchmarks focus on isolated interactions, failing to capture cross-session reasoning. We introduce a framework for synthesizing high-quality, long-term medical dialogues with LLMs. Our approach entails a knowledge-guided decomposition into three stages: constructing synthetic patient profiles with diverse disease and complication trajectories, generating multiturn dialogues per encounter, and integrating them into a coherent longitudinal history dataset, MediLongChat. We establish three …

Open Source Software Development Tool Installation: Challenges And Strategies For Novice Developers, Larissa Salerno, Christoph Treude, Patanamon Thongtanunam

Research Collection School Of Computing and Information Systems

As the world of technology advances, so do the tools that software developers use to create new programs. In recent years, software development tools have become more popular, allowing developers to work more efficiently and produce higher-quality software. Still, installing such tools can be challenging for novice developers at the early stage of their careers, as they may face issues such as compatibility problems (e.g., with operating systems) and unclear instructions. Therefore, this work aims to investigate the challenges novice developers face when installing software development tools and the strategies they employ to overcome them. To investigate these, we conducted …

Mease: Multi-Agent Episodic Action Sequence Explanation, Phyo Wai Khaing, Minghong Geng, Shubham Pateria, Budhitama Subagdja, Ah-Hwee Tan

Research Collection School Of Computing and Information Systems

Multi-agent reinforcement learning (MARL) achieves remarkable performance in complex coordination tasks, yet interpreting the emergent behaviors of trained agents remains a fundamental challenge. Most current explainability methods focus on individual agent decisions, overlooking the critical interplay of joint strategiesand temporal coordination patterns that define successful multi-agent policies. We present MEASE (Multi-agent Episodic Action Sequence Explanation), a novel explainable MARL (XMARL) framework that explains trained MARL policies as human-interpretable emergent cooperative joint behaviors. MEASE employs a cognition-inspired episodic memory model to learn spatio-temporal multi-agent interaction patterns, coupled with abstraction algorithms that identify significant cooperative agent behaviors. We evaluate MEASE on diverse …

Generation Of Elaborated, Targeted And Effective Feedback For Novice Programmers Using Llm, Hua Leong Fwa

Research Collection School Of Computing and Information Systems

Programming errors and misconceptions are pervasive in novice programmers which causes difficulty in the learning of computer programming. Large Language Models (LLMs), with their ability to comprehend and generate programming codes have shown promising results in the automatic identification of errors. This can potentially benefit student programmers by providing them with timely formative feedback at efficiencies and scale that were not attainable previously. In this study, we leveraged an LLM - OpenAI o4-mini for the generation of elaborated, targeted feedback for novice programmers across PHP and JavaScript exercises. We contend that the feedback needs to be effective and targeted other …

Securing Cloud-Native Systems: From Vulnerability Analysis To External And Insider Threat Detection, Jiongchi Yu

Dissertations and Theses Collection (Open Access)

Cloud-native systems have become the backbone of modern software infrastructure. However, their dynamic resource orchestration and complex configurability introduce a large attack surface and intricate security challenges. Adversaries can externally exploit vulnerabilities in cloud components or perform insider movement within cloud environments to launch attacks. As these systems increasingly support critical services, security breaches can lead to severe operational and economic consequences.

Despite extensive efforts in vulnerability detection and attack monitoring, existing approaches struggle to remain effective in cloud-native environments characterized by rapid evolution and inherent heterogeneity. In particular, they exhibit three fundamental limitations: (1) Insufficient understanding of defect patterns …

Market Reactions To Deceptive Language In Fake News: Implications From Language Expectancy Theory And Transfer Learning, Ka Chung Ng, Ping Fan Ke, Ping Fan, Mike So, Tam, Kar Yan

Research Collection School Of Computing and Information Systems

The advent of generative artificial intelligence (AI) has heightened the proliferation of fake news. A key challenge is the limited real-world data to investigate the societal impact of fake news produced by generative AI. In this paper, we examine stock market reactions to financial news articles that exhibit stylometric similarity to human-crafted and AI-crafted fake financial news. Grounded in language expectancy theory, we employ a style-based transfer learning model, pre-trained to recognizing deceptive language employed in various types of fake news intricacies. We then apply this model to a comprehensive dataset of financial news, assigning a “veracity style score” to …

Natural Adversaries: Fuzzing Autonomous Vehicles With Realistic Roadside Object Placements, Yang Sun, Haoyu Wang, Christopher M. Poskitt, Jun Sun

Research Collection School Of Computing and Information Systems

The emergence of Autonomous Vehicles (AVs) has spurred research into testing the resilience of their perception systems, i.e., ensuring that they are not susceptible to critical misjudgements. It is important that these systems are tested not only with respect to other vehicles on the road, but also with respect to objects placed on the roadside. Trash bins, billboards, and greenery are examples of such objects, typically positioned according to guidelines developed for the human visual system, which may not align perfectly with the needs of AVs. Existing tests, however, usually focus on adversarial objects with conspicuous shapes or patches, which …

Detecting Doubt In Reflective Learning: A Learning Analytics Study With Large And Small Language Models, Eng Lieh Ouh, Kar Way Tan, Siaw Ling Lo, Yuhao Zhang

Research Collection School Of Computing and Information Systems

Reflective learning enhances understanding, especially when instructors promptly address difficulties raised in student reflections. Automated doubt detection can reduce time for instructors, yet existing classification approaches take substantial time for manual annotation and model training. This paper investigates whether large and small language models (LLMs, SLMs) can automate doubt detection without time-consuming training. Using a dataset of anonymized student reflections, we evaluate zeroshot, few-shot prompting, and multi-step reasoning against prior supervised classification baselines. We show that LLMs (GPT-4o, Claude-4, Gemini-2.5) surpass earlier F1 scores without prompting, while prompting further improves their performance. However, using proprietary LLMs can raise cost and …

Sevoauth: Secure Voiceprint Authentication With Hash-Based Feature Transformation, Rui Zhang, Zheng Yan, Robert H. Deng

Research Collection School Of Computing and Information Systems

While voiceprint authentication offers convenient user authentication and access control through voice feature recognition, a critical research gap remains: existing voiceprint authentication systems fail to simultaneously achieve sound security against replay, spoofing, and adversarial attacks, preserve voice privacy leakage, and satisfy usability demand. Previous efforts have struggled to balance these issues comprehensively. To bridge this gap, we present SeVoAuth, a cloud-based Voiceprint Authentication as a Service (VAaaS) system designed to provide privacy preservation, robust security, and enhanced usability. SeVoAuth stores a synthesized voiceprint of a user in the cloud during user registration, thereby safeguarding the privacy of the real voiceprint …

Quantitative Bounds On Resource Usage Of Probabilistic Programs, Krishnendu Chatterjee, Amir Kafshdar Goharshady, Tobias Meggendorfer, Dorde Zikelic

Research Collection School Of Computing and Information Systems

Cost analysis, also known as resource usage analysis, is the task of finding bounds on the total cost of a program and is a well-studied problem in static analysis. In this work, we consider two classical quantitative problems in cost analysis for probabilistic programs. The first problem is to find a bound on the expected total cost of the program. This is a natural measure for the resource usage of the program and can also be directly applied to average-case runtime analysis. The second problem asks for a tail bound, i.e. ‍given a threshold t the goal is to find …

Fighting Against Recruitment Scams: Theory-Driven Supervised Learning And Empirical Analysis For Digital Fraudulent Recruitment Posting Behavior, Tom (Tianteng) Wang, David (Jingjun) Xu, Keng Siau, Zhongju (John) Zhang

Research Collection School Of Computing and Information Systems

The number of recruitment postings on digital recruitment hiring platforms has increased since the COVID-19 pandemic. However, the weak surveillance and operations of these platforms, combined with the fact that most job seekers have relatively low vigilance and a strong desire for recruitment offers, enable scammers to easily deceive job seekers for their money and confidential information. In this work, we combine prevailing text mining techniques (i.e., ChatGPT with prompting engineering and supervised machine learning) with interpersonal deception theory (IDT) from social science to design an interpretable IT system to predict fraudulent recruitment postings on digital recruitment-hiring platforms. We compare …

Enhancing Action And Ingredient Modeling For Semantically Grounded Recipe Generation, Guoshan Liu, Bin Zhu, Yian Li, Jingjing Chen, Chong-Wah Ngo, Yu-Gang Jiang

Research Collection School Of Computing and Information Systems

Recent advances in Multimodal Large Language Models (MLMMs) have enabled recipe generation from food images, yet outputs often contain semantically incorrect actions or ingredients despite high lexical scores (e.g., BLEU, ROUGE). To address this gap, we propose a semantically grounded framework that predicts and validates actions and ingredients as internal context for instruction generation. Our two-stage pipeline combines supervised fine-tuning (SFT) with reinforcement fine-tuning (RFT): SFT builds foundational accuracy using an Action-Reasoning dataset and ingredient corpus, while RFT employs frequency-aware rewards to improve long-tail action prediction and ingredient generalization. A Semantic Confidence Scoring and Rectification (SCSR) module further filters and …

Selective Concolic Testing, Guofeng Zhang, Zhenbang Chen, Ziqi Shuai, Jun Sun, Weijiang Hong, Yufeng Zhang, Ji Wang, Yang Liu

Research Collection School Of Computing and Information Systems

The principled combination of symbolic execution and random testing lacks a formal foundation, especially in deciding which inputs to symbolize. We propose selective concolic testing, a cost-aware framework that formulates this choice as an optimized policy problem of a MDP (Markov Decision Process). We model program exploration over a finite control-flow graph, where MDP states represent covered statements, actions partition path constraints into symbolic and random fragments, rewards reflect coverage gain, and costs account for SMT solving effort and sampling inefficiency. Our framework yields the first formal characterization of selective symbolization as policy synthesis in a probabilistic system. We prove …

Understanding Critical Thinking In Generative Artificial Intelligence Use: Development, Validation, And Correlates Of The Critical Thinking In Ai Use Scale, Gabriel R. Lau, Wei Yan Low, Louis Tay, Ysabel Thereze Ang Guevarra, Dragon Gašević, Andree Hartanto

Research Collection School of Social Sciences

Generative AI tools are increasingly embedded in everyday work and learning, yet their fluency, opacity, and propensity to hallucinate mean that users must critically evaluate AI outputs rather than accept them at face value. The present research conceptualises critical thinking in AI use as a dispositional tendency to verify the source and content of AI-generated information, to understand how models work and where they fail, and to reflect on the broader implications of relying on AI. Across six studies ( N = 1341), we developed and validated the 13-item critical thinking in AI use scale and mapped its nomological network. …

Digital Grief Technology To Support Bereavement: A Systematic Review Of Potential Benefits And Risks, Xun Ci Soh, Adalia Yin Hui Goh, Paye Shin Koh, Andree Hartanto

Research Collection School of Social Sciences

Grief is a universal and inevitable experience. However, the way we support the bereaved is changing, especially in the digital era. This systematic review examines the potential benefits and risks associated with various digital grief technologies, including online grief support groups, generative AI chatbots, online memorials, online therapy interventions, virtual reality, and digitally reproduced visuals or audio of the deceased. A systematic search was conducted in seven databases, and 30 articles were included in the final review. Findings indicate that digital grief technologies offer several benefits, such as reductions in grief and depressive symptoms, enhanced social support, greater accessibility, and …

Where Did It Go Wrong? Attributing Undesirable Llm Behaviors Via Representation Gradient Tracing, Zhe Li, Wei Zhao, Yige Li, Jun Sun

Research Collection School Of Computing and Information Systems

Large Language Models (LLMs) have demonstrated remarkable capabilities, yet their deployment is frequently undermined by undesirable behaviors such as generating harmful content, factual inaccuracies, and societal biases. Diagnosing the root causes of these failures poses a critical challenge for AI safety. Existing attribution methods, particularly those based on parameter gradients, often fall short due to prohibitive noisy signals and computational complexity. In this work, we introduce a novel and efficient framework that diagnoses a range of undesirable LLM behaviors by analyzing representation and its gradients, which operates directly in the model's activation space to provide a semantically meaningful signal linking …

Architecture-Agnostic Test-Time Adaptation Via Backprop-Free Embedding Alignment, Xiao Ma, Young D. Kwon, Pan Zhou, Dong Ma

PhD Student’s Publications Collection

Test-Time Adaptation (TTA) adapts a deployed model during online inference to mitigate the impact of domain shift. While achieving strong accuracy, most existing methods rely on backpropagation, which is memory and computation intensive, making them unsuitable for resource-constrained devices. Recent attempts to reduce this overhead often suffer from high latency or are tied to specific architectures such as ViT-only or CNN-only. In this work, we revisit domain shift from an embedding perspective. Our analysis reveals that domain shift induces three distinct structural changes in the embedding space: translation (mean shift), scaling (variance shift), and rotation (covariance shift). Based on this …

Scalable Multi-Task Low-Rank Model Adaptation, Zichen Tian, Antoine Ledent, Qianru Sun

PhD Student’s Publications Collection

Scaling multi-task low-rank adaptation (LoRA) to a large number of tasks induces catastrophic performance degradation, such as an accuracy drop from 88.2% to 2.0% on DOTA when scaling from 5 to 15 tasks. This failure is due to parameter and representation misalignment. We find that existing solutions, like regularization and dynamic routing, fail at scale because they are constrained by a fundamental trade-off: strengthening regularization to reduce inter-task conflict inadvertently suppresses the essential feature discrimination required for effective routing. In this work, we identify two root causes for this trade-off. First, uniform regularization disrupts inter-task knowledge sharing: shared underlying knowledge …

Discrete Diffusion For Bundle Construction, Teng Tu, Ai Li, Yunshan Ma, Shuo Xu, Xiaohao Liu, Haokai Ma, Liang Pang, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

As a central task in product bundling, bundle construction aims to select a subset of items from large item catalogs to build an entire bundle or, more practically, complete a partial bundle. Existing methods often rely on the sequential construction paradigm that predicts items one at a time, nevertheless, this paradigm is fundamentally unsuitable for the essentially unordered bundles. In contrast, non-sequential methods model a bundle as a set, but still face two dimensionality curses: the combinatorial space grows exponentially with both bundle length and catalog size. Accordingly, we identify two technical challenges: 1) how to effectively and efficiently model …

Ai Models As Cultural Beings: Investigating Ai Cultural Biases And The Impact Of Cultural Alignment On Human-Ai Creative Collaboration, Choon Ngee Tan, Meng Han, Roy Y. J. Chua, Chi-Ying Cheng

Research Collection Lee Kong Chian School Of Business

Existing research on AI cultural biases predominantly focuses on Western models, overlooking critical gaps in non-Western models. We conduct a comparative analysis of AI models – ChatGPT (U.S. developed) and ErnieBot (China developed) – from different cultures to investigate how corresponding cultural biases manifest in their outputs. Additionally, we examine how cultural alignment between human users and AI models impacts their collaborative creative performance and the underlying psychological mechanisms. In Study 1, multi-choice prompt with zero-shot technique was used to evaluate cultural biases in four widely used AI models – ChatGPT-3.5/4, ErnieBot-3.5/4 – comparing their responses to established cultural psychometric …

Portrait Shadow Removal Via Self-Exemplar Illumination Equalization, Qian Huang, Cheng Xu, Guiqing Li, Ziheng Wu, Shengxin Liu, Shengfeng He

Research Collection School Of Computing and Information Systems

We introduce the Self-Exemplar Illumination Equalization Network, designed specifically for effective portrait shadow removal. The core idea of our method is that partially shadowed portraits can find ideal exemplars within their non-shadowed facial regions. Rather than directly fusing two distinct classes of facial features, our approach utilizes non-shadowed regions as an illumination indicator to equalize the shadowed regions, generating deshadowed results without boundary-merging artifacts. Our network comprises cascaded Self-Exemplar Illumination Equalization Blocks (SExmBlock), each containing two modules: a self-exemplar feature matching module and a feature-level illumination rectification module. The former identifies and applies internal illumination exemplars to shadowed areas, producing …

Weakly Supervised Video Anomaly Detection And Localization With Spatio-Temporal Prompts, Peng Wu, Xuerong Zhou, Guansong Pang, Zhiwei Yang, Qingsen Yan, Peng Wang, Yanning Zhang

Research Collection School Of Computing and Information Systems

Current weakly supervised video anomaly detection (WSVAD) task aims to achieve frame-level anomalous event detection with only coarse video-level annotations available. Existing works typically involve extracting global features from full-resolution video frames and training frame-level classifiers to detect anomalies in the temporal dimension. However, most anomalous events tend to occur in localized spatial regions rather than the entire video frames, which implies existing frame-level feature based works may be misled by the dominant background information and lack the interpretation of the detected anomalies. To address this dilemma, this paper introduces a novel method called STPrompt that learns spatio-temporal prompt embeddings …

Trace: Securing Smart Contract Repository Against Access Control Vulnerability, Chong Chen, Lingfeng Bao, David Lo, Yanlin Wang, Zhenyu Shan, Ting Chen, Guangqiang Yin, Jianxing Yu, Zibin Zheng, Jiachi Chen

Research Collection School Of Computing and Information Systems

Smart contract vulnerabilities have led to billions of dollars in economic losses. Among these, improper Access Control, which allows unauthorized users to execute restricted functions, is particularly prevalent and has caused significant financial damage. Smart contract repositories contain source code, documentation, configuration files, and other artifacts necessary for building and deploying smart contracts. GitHub hosts numerous open-source repositories of this kind, which serve as intermediate artifacts in development and require compilation and packaging to produce deployable contracts. Third-party developers often reference, reuse, or fork code from these repositories during custom development. However, if the referenced code contains vulnerabilities, it can …

Super Lidar Intensity For Robotic Perception, Wei Gao, Jie Zhang, Mingle Zhao, Zhiyuan Zhang, Shu Kong, Maani Ghaffari, Dezhen Song, Chengzhong Xu, Hui Kong

Research Collection School Of Computing and Information Systems

Conventionally, human intuition defines vision as a modality of passive optical sensing, relying on ambient light to perceive the environment. However, active optical sensing, which involves emitting and receiving signals, offers unique advantages by capturing both radiometric and geometric properties of the environment, independent of external illumination conditions. This work focuses on advancing active optical sensing using Light Detection and Ranging (LiDAR), which captures intensity data, enabling the estimation of surface reflectance that remains invariant under varying illumination. Such properties are crucial for robotic perception tasks, including detection, recognition, segmentation, and Simultaneous Localization and Mapping (SLAM). A key challenge with …

Managing Reproducibility Debt In Scientific Software: A Practical Framework, Zara Hassan, Christoph Treude, Graham Williams, Michael Norrish, Alex Potanin

Research Collection School Of Computing and Information Systems

Scientific software includes end-user applications, modelling tools, research software for publications, and production systems for real users. It plays a key role across various scientific disciplines by enabling large-scale computation, simulation, and data analysis. Unlike commercial software, scientific software is often developed in dynamic research environments with limited engineering practices, documentation, or testing. This makes it fragile and difficult to reproduce results, even when code and data are available, conditions in which Reproducibility Debt (RpD) accumulates. This paper presents the Reproducibility Debt Management Framework (RpD-MF), which is grounded in evidence from a systematic literature review, practitioner interviews, and a global …

Llmqua: Practical Backdoor Injection On Large Language Model Quantization, Xiangxiang Chen, Peixin Zhang, Jun Sun, Jin Song Dong, Wenhai Wang, Jingyi Wang

Research Collection School Of Computing and Information Systems

Quantization is widely used to enable local deployment of large language models (LLMs) on resource-constrained devices. Recent work (e.g., QuRA) shows quantization can be exploited via rounding manipulation to implant backdoors. However, such an attack has been evaluated only on small models and does not directly apply to LLMs due to three key constraints: (1) limited poisoning data from small, task-agnostic calibration sets; (2) layer-wise quantization restricting adversarial access to global representations; and (3) lack of gradient access in quantization pipelines, blocking gradient-based attacks.We propose LLMQuA, a practical quantization-phase backdoor attack tailored to the LLM setting. LLMQuA (i) injects backdoors …

Generative Ai In Enterprises: Optimizing Applications With Large Language Models, Donghao Huang

Dissertations and Theses Collection (Open Access)

This dissertation investigates how to deploy Large Language Models (LLMs) effectively in enterprise settings, where accuracy, reliability, cost, privacy, and operational constraints often matter more than benchmark performance alone. Drawing on seventeen peer-reviewed publications (eleven published and six accepted for publication), the work develops and validates optimization strategies across three connected themes: retrieval-augmented generation (RAG), agentic AI for workflow automation, and deployment guidelines for real-world enterprise environments.

First, we study RAG optimization through systematic evaluation of open and proprietary models, highlighting conditions under which efficient open-weight models can match or exceed proprietary alternatives. To address a pervasive failure mode in …

Reducing Class-Wise Performance Disparity Via Margin Regularization, Beier Zhu, Kesen Zhao, Jiequan Cui, Qianru Sun, Yuan Zhou, Xun Yang, Hanwang Zhang

Research Collection School Of Computing and Information Systems

Deep neural networks often exhibit substantial disparities in class-wise accuracy, even when trained on class-balanced data—posing concerns for reliable deployment. While prior efforts have explored empirical remedies, a theoretical understanding of such performance disparities in classification remains limited. In this work, we present Margin Regularization for performance disparity Reduction (MR2 ), a theoretically principled regularization for classification by dynamically adjusting margins in both the logit and representation spaces. Our analysis establishes a margin-based, class-sensitive generalization bound that reveals how per-class feature variability contributes to error, motivating the use of larger margins for “hard” classes. Guided by this insight, MR2 optimizes …

Who You Explain To Matters: Learning By Explaining To Conversational Agents With Different Pedagogical Roles, Zhengtao Xu, Junti Zhang, Anthony Tang, Yi-Chieh Lee

Research Collection School Of Computing and Information Systems

Conversational agents are increasingly used in education for learning support. An application is “learning by explaining”, where learners explain their understanding to an agent. However, existing research focuses on single roles, leaving it unclear how different pedagogical roles influence learners’ interaction patterns, learning outcomes and experiences. We conducted a between-subjects study (N=96) comparing agents with three pedagogical roles (Tutee, Peer, Challenger) and a control condition while learning an economics concept. We found that different pedagogical roles shaped learning dynamics, including interaction patterns and experiences. Specifically, the Tutee agent elicited the most cognitive investment but led to high pressure. The Peer …

Think First, Chatgpt Later: Guiding Human-Ai Collaboration For Learning Gains In Independent Human Creativity, Sarah Shi Hui Wong, Sophia Xuefei Qiu

Research Collection School of Social Sciences

Generative artificial intelligence (AI) tools such as ChatGPT can boost creative performance, but do these boosts translate into learning gains? This study examined whether the benefits of ChatGPT for creativity persist even when its assistance is removed, and how people can effectively use ChatGPT to enhance their learning and independent creativity. University students (N = 196) solved a creative product improvement task either independently (human-only group) or using ChatGPT freely (general-AI group) or using ChatGPT in a guided way (regulated-AI group). Specifically, the regulated-AI group used a novel “think first, ChatGPT later” approach—they first generated their own ideas, then collaborated …