Digital Commons Network^™

Assessing The Robustness Of Test Selection Methods For Deep Neural Networks, Qiang Hu, Yuejun Guo, Xiaofei Xie, Maxime Cordy, Wei Ma, Mike Papadakis, Lei Ma, Yves Le Traon

Research Collection School Of Computing and Information Systems

Regularly testing deep learning-powered systems on newly collected data is critical to ensure their reliability, robustness, and efficacy in real-world applications. This process is demanding due to the significant time and human effort required for labeling new data. While test selection methods alleviate manual labor by labeling and evaluating only a subset of data while meeting testing criteria, we observe that such methods with reported promising results are simply evaluated, e.g., testing on original test data. The question arises: are they always reliable? In this article, we explore when and to what extent test selection methods fail. First, we identify …

How To Enable Effective Cooperation Between Humans And Nlp Models: A Survey Of Principles, Formalizations, And Beyond, Chen Huang, Yang Deng, Wenqiang Lei, Jiancheng Lv, Tat-Seng Chua, Jimmy Huang

Research Collection School Of Computing and Information Systems

With the advancement of large language models (LLMs), intelligent models have evolved from mere tools to autonomous agents with their own goals and strategies for cooperating with humans. This evolution has birthed a novel paradigm in NLP, i.e., human-model cooperation, that has yielded remarkable progress in numerous NLP tasks in recent years. In this paper, we take the first step to present a thorough review of human-model cooperation, exploring its principles, formalizations, and open challenges. In particular, we introduce a new taxonomy that provides a unified perspective to summarize existing approaches. Also, we discuss potential frontier areas and their corresponding …

Fact-Audit: An Adaptive Multi-Agent Framework For Dynamic Fact-Checking Evaluation Of Large Language Models, Hongzhan Lin, Yang Deng, Yuxuan Gu, Wenxuan Zhang, Jing Ma, See-Kiong Ng, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Large Language Models (LLMs) have significantly advanced the fact-checking studies. However, existing automated fact-checking evaluation methods rely on static datasets and classification metrics, which fail to automatically evaluate the justification production and uncover the nuanced limitations of LLMs in fact-checking. In this work, we introduce FACT-AUDIT, an agent-driven framework that adaptively and dynamically assesses LLMs’ fact-checking capabilities. Leveraging importance sampling principles and multi-agent collaboration, FACT-AUDIT generates adaptive and scalable datasets, performs iterative model-centric evaluations, and updates assessments based on model-specific responses. By incorporating justification production alongside verdict prediction, this framework provides a comprehensive and evolving audit of LLMs’ factual reasoning …

Beware Of Your Po! Measuring And Mitigating Ai Safety Risks In Role-Play Fine-Tuning Of Llms, Weixiang Zhao, Yulin Hu, Yang Deng, Jiahe Guo, Xingyu Sui, Xinyang Han, An Zhang, Yanyan Zhao, Bing Qin, Tat-Seng Chua, Ting Liu

Research Collection School Of Computing and Information Systems

Although large language models (LLMs) store vast amount of knowledge in their parameters, they still have limitations in the memorization and utilization of certain knowledge, leading to undesired behaviors such as generating untruthful and inaccurate responses. This highlights the critical need to understand the knowledge boundary of LLMs, a concept that remains inadequately defined in existing research. In this survey, we propose a comprehensive definition of the LLM knowledge boundary and introduce a formalized taxonomy categorizing knowledge into four distinct types. Using this foundation, we systematically review the field through three key lenses: the motivation for studying LLM knowledge boundaries, …

Browsing Like Human: A Multimodal Web Agent With Experiential Fast-And-Slow Thinking, Haohao Luo, Jiayi Kuang, Wei Liu, Ying Shen, Jian Luan, Yang Deng

Research Collection School Of Computing and Information Systems

Automating web navigation which aims to build a web agent that follows user instructions to complete tasks like booking flights by interacting with websites, has received increasing attention due to its practical value. Although existing web agents are mostly equipped with visual perception, planning, and memory abilities, their reasoning process are still deviate from human cognition. In this work, we study the human thought pattern to empower agent with more human-like abilities in web navigation. To tackle this problem, we propose a novel multimodal web agent framework called WebExperT, which is designed to emulate the human planning process of “thinking …

Other Orienteering Problem Variants, Pieter Vansteenwegen, Aldy Gunawan

Research Collection School Of Computing and Information Systems

In this chapter, different variants of routing problems with profits will be discussed. Based on what is available in literature, mostly variants of the orienteering problem will be discussed. A first variant considers capacity constraints, since these appear frequently in many practical applications. Next, multi-objective orienteering problems, explicitly considering different types of profits separately are discussed. Time-dependent and stochastic travel times are also relevant for most practical applications. These are considered together with time-dependent and stochastic profits. More and more routing problems are considered together with inventory management. For routing problems with profits, this leads to the inventory orienteering problem, …

Optimizing Group Utility In Itinerary Planning: A Strategic And Crowd-Aware Approach, Junhua Liu, Aldy Gunawan, Kristin L. Wood, Kwan Hui Lim

Research Collection School Of Computing and Information Systems

Itinerary recommendation is a complex sequence prediction problem with numerous practical applications. The task becomes significantly more challenging when optimizing multiple factors simultaneously, such as user queuing times, crowd levels, attraction popularity, walking durations, and operating hours. These factors, combined with the dynamic and unpredictable nature of visitor flow, introduce substantial complexities, particularly when accounting for collective user behavior. Existing solutions often adopt a single-user perspective, overlooking critical challenges arising from natural crowd dynamics. For example, the Selfish Routing problem illustrates how individual decision-making can lead to suboptimal outcomes for the group as a whole. To address these challenges, we …

A Review: The Beauty Of Serendipity Between Integrated Circuit Security And Artificial Intelligence, Chen Dong, Decheng Qiu, Bolun Li, Yang Yang, Chenxi Lyu, Dong Cheng, Hao Zhang, Zhenyi. Chen

Research Collection School Of Computing and Information Systems

Integrated circuits are the core of a cyber-physical system, where tens of billions of components are integrated into a tiny silicon chip to conduct complex functions. To maximize utilities, the design and manufacturing life cycle of integrated circuits rely on numerous untrustworthy third parties, forming a global supply chain model. At the same time, this model produces unpredictable and catastrophic issues, threatening the security of individuals and countries. As for guaranteeing the security of ultra-highly integrated chips, detecting slight abnormalities caused by malicious behavior in the current and voltage is challenging, as is achieving computability within a reasonable time and …

Causalabstain: Enhancing Multilingual Llms With Causal Reasoning For Trustworthy Abstention, Yuxi Sun, Aoqi Zuo, Wei Gao, Jing Ma

Research Collection School Of Computing and Information Systems

Large Language Models (LLMs) often exhibit knowledge disparities across languages. Encouraging LLMs to abstain when faced with knowledge gaps is a promising strategy to reduce hallucinations in multilingual settings. Current abstention strategies for multilingual scenarios primarily rely on generating feedback in various languages using LLMs and performing self-reflection. However, these methods can be adversely impacted by inaccuracies and biases in the generated feedback. To address this, from a causal perspective, we introduce CausalAbstain, a method that helps LLMs determine whether to utilize multiple generated feedback responses and how to identify the most useful ones. Extensive experiments demonstrate that CausalAbstain effectively …

Advancing Molecular Graph-Text Pre-Training Via Fine-Grained Alignment, Yibo Li, Yuan Fang, Mengmei Zhang, Chuan Shi

Research Collection School Of Computing and Information Systems

Understanding molecular structure and related knowledge is crucialfor scientific research. Recent studies integrate molecular graphswith their textual descriptions to enhance molecular representationlearning. However, they focus on the whole molecular graph andneglect frequently occurring subgraphs, known as motifs, whichare essential for determining molecular properties. Without suchfine-grained knowledge, these models struggle to generalize to un-seen molecules and tasks that require motif-level insights. To bridgethis gap, we propose FineMolTex, a novel Fine-grained Moleculargraph-Text pre-training framework to jointly learn coarse-grainedmolecule-level knowledge and fine-grained motif-level knowledge.Specifically, FineMolTex consists of two pre-training tasks: a con-trastive alignment task for coarse-grained matching and a maskedmulti-modal modeling task for …

Equivalence And Similarity Refutation For Probabilistic Programs, Krishnendu Chatterjee, Ehsan Kafshdar Goharshady, Petr Novotný, Dorde Zikelic

Research Collection School Of Computing and Information Systems

We consider the problems of statically refuting equivalence and similarity of output distributions defined by a pair of probabilistic programs. Equivalence and similarity are two fundamental relational properties of probabilistic programs that are essential for their correctness both in implementation and in compilation. In this work, we present a new method for static equivalence and similarity refutation. Our method refutes equivalence and similarity by computing a function over program outputs whose expected value with respect to the output distributions of two programs is different. The function is computed simultaneously with an upper expectation supermartingale and a lower expectation submartingale for …

Graph Positional Autoencoders As Self-Supervised Learners, Yang Liu, Deyu Bo, Wenxuan Cao, Yuan Fang, Yawen Li, Chuan Shi

Research Collection School Of Computing and Information Systems

Graph self-supervised learning seeks to learn effective graph representations without relying on labeled data. Among various approaches, graph autoencoders (GAEs) have gained significant attention for their efficiency and scalability. Typically, GAEs take incomplete graphs as input and predict missing elements, such as masked node features or edges. Although effective, our experimental investigation reveals that traditional feature or edge masking paradigms primarily capture low-frequency signals in the graph and fail to learn expressive structural information. To address these issues, we propose Graph Positional Autoencoders (GraphPAE), which employ a dual-path architecture to reconstruct both node features and positions. Specifically, the feature path …

L2m2: A Hierarchical Framework Integrating Large Language Model And Multi‑Agent Reinforcement Learning, Minghong Geng, Shubham Pateria, Budhitama Subagdja, Lin Li, Xin Zhao, Ah-Hwee Tan

Research Collection School Of Computing and Information Systems

Multi-agent reinforcement learning (MARL) has demonstrated remarkable success in collaborative tasks, yet faces significant challenges in scaling to complex scenarios requiring sustained planning and coordination across long horizons. While hierarchical approaches help decompose these tasks, they typically rely on hand-crafted subtasks and domain-specific knowledge, limiting their generalizability. We present L2M2, a novel hierarchical framework that leverages large language models (LLMs) for high-level strategic planning and MARL for low-level execution. L2M2 enables zero-shot planning that supports both end-to-end training and direct integration with pre-trained MARL models. Experiments in the VMAS environment demonstrate that L2M2's LLM-guided MARL achieves superior performance while requiring …

Ai-Assisted Risk Assessment In Generative Ai Governance, Wu Jiaqi Young, Fiona Fui-Hoon Nah

Research Collection School Of Computing and Information Systems

Effective risk assessment is paramount for responsible generative AI (GenAI) deployment. Traditional governance approaches that rely on manual reviews are inadequate given the scale and velocity of GenAI outputs. A risk-based approach incorporating real-time monitoring and governance is paramount. In this research, we examine how the efficacy of suggestive versus supportive explanations for AI’s risk assessment of GenAI outputs is moderated by user domain expertise and AI’s risk assessment in determining user acceptance. We hypothesize that cognitive involvement increases with AI’s risk assessment, with higher risks triggering more critical evaluation. By drawing on the elaboration likelihood model, we hypothesize that …

Judicial Independence, The Separation Of Powers, And Criminal Investigations Of Judges, Benjamin Joshua Ong

Research Collection Yong Pung How School Of Law

In Haris Ibrahim [2023] 2 MLJ 296, the Federal Court of Malaysia discussed the legal limits to executive authorities’ powers to investigate judges on suspicion of crime. The case is a rare contribution to the jurisprudence on judges’ criminal liability at common law, as well as a case study in the challenges of reconciling judicial independence with other principles of the constitutional framework and other actors’ roles therein. The Court held that the implied constitutional principle of judicial independence requires that executive authorities follow a “set of protocols” (which the Court formulated) when investigating sitting judges. This was not wrong …

Trust In Healthcare Ai Can’T Just Be Designed – It Must Be Felt By Clinicians And Patients, Adriana Banozic-Tang, Heng Wang

Research Collection Yong Pung How School Of Law

Trust in healthcare AI currently over-relies on system design, not lived medical realities.Continuous feedback loops are necessary to embed trust in healthcare AI that is responsive to clinician and patient needs.Initiatives in South-East Asia show how trust in technology can be extended from policy to practice.

Ai In The Judiciary: The Singapore Case, Nydia Remolina Leon

Research Collection Yong Pung How School Of Law

This paper examines the integration of Artificial Intelligence (AI) within the judicial system of Singapore. Singapore's judiciary has embraced AI not as a tool for adjudication, but as an augmentative instrument for legal research, procedural efficiency, and access to justice. It provides a detailed account of AI use cases in the courts, including case summarization, evidence review, assistance for selfrepresented litigants, and tools like the Divorce Assets Informative Division Estimator. The discussion then turns to the legal profession, exploring how law firms in Singapore are adopting AI technologies. The paper also addresses how AI implementation in the judicial system is …

Would Order-By-Order Auctions Be Competitive?, Thomas Ernst, Chester Spatt, Jian Sun

Research Collection Lee Kong Chian School Of Business

We model two methods of executing segregated retail orders: brokers’ routing,whereby brokers allocate orders using the market maker’s overall performance, andorder-by-order auctions, where market makers bid on individual orders, a recent U.S.Securities and Exchange Commission proposal. Order-by-order auctions improve al-locative efficiency, but face a winner’s curse reducing retail investor welfare, partic-ularly when liquidity is limited. Additional market participants competing for retailorders fail to improve total efficiency and investor welfare when entrants possess in-formation superior to incumbent wholesalers. Our results hold when new entrants are less informed or the information structure differs. We also examine the cross-subsidization of brokers’ routing.

Faced With Genai, Educators’ Engagement Capacity Matters More Than Ever, Thomas Menkhoff

Research Collection Lee Kong Chian School Of Business

In a commentary, SMU Professor of Organisational Behaviour & Human Resources (Education) Thomas Menkhoff stressed the need for educators to upskill so they can guide students in using generative artificial intelligence (GenAI) responsibly, rather than dismissing it. He argued that universities should move beyond prohibition and invest in AI literacy to safeguard academic integrity. Prof Menkhoff mentioned that combining the use of GenAI tools with effective prompting and Socratic questioning transforms students’ use of technology from passive consumption to active, reflective and critical engagement. To achieve this, he said that schools must set clear guidelines and design AI-compatible assessments that …

Innovate, Collaborate, Lead: The Global Library Leaders’ Toolkit, Shameem Nilofar Maideen

Research Collection Library

The Strategic Leadership Reality Our Challenge : How do you build strategic value while maintaining operational excellence with constrained resources?

Nurturing Change Makers: Best Practices From Smu Libraries, Shameem Nilofar Maideen

Research Collection Library

No abstract provided.

Physical Work Environments: An Integrative Review And Agenda For Future Research, Bukky Akinsanmi Oyedeji, Yea Hee Ko, Sunkee Lee

Research Collection Lee Kong Chian School Of Business

This review examines the effect of physical work environments—the dedicated, tangible spaces where employees carry out their professional tasks—on organizational processes and outcomes. We synthesize decades of research across various disciplines using a conceptual framework that defines physical work environments along three key dimensions: ambience, spatial configuration, and aesthetics. These dimensions are analyzed for their effects on both internal stakeholders, such as employees, and external stakeholders, including clients, suppliers, and investors. Our analysis reveals two major themes in prior research: (1) task accomplishment, which focuses on how physical work environments influence physical and mental health, motivation and attitudes, as well …

A Power Dependence Model Of The Impact Of Leader Impostorism On Supervisor Support And Undermining: The Moderating Role Of Power Distance, Zihan Liu, Zihan Liu, Feng Qiu, Keith Leavitt, Xingyu Wang, Ziyang Tang

Research Collection Lee Kong Chian School Of Business

Leaders, often perceived as possessing exceptional confidence and competence, are not immune to feelings of self-doubt. Leader impostorism describes the experience that one’s attributes, experiences, skills, and abilities fall short of the standards expected in the leadership role, resulting in a sense of deception in fulfilling leadership responsibilities. While existing research has examined the antecedents and individual outcomes of leader impostorism, its implications for leaders’ treatment of subordinates remain largely unexplored. In this research, we investigate the downstream consequences of leader impostorism on behaviors directed toward subordinates. Integrating research on leader impostorism with power dependence theory, we propose that for …

One-Sided Limited Commitment And Aggregate Risk, Yoshiki Ando, Dirk Krueger, Harald Uhlig

Research Collection School Of Economics

In this paper we study the neoclassical growth model with idiosyncratic income risk and aggregate risk in which risk sharing is endogenously constrained by one sided limited commitment. Households can trade a full set of contingent claims that pay off depending on both idiosyncratic and aggregate risk, but limited commitment rules out that households sell these assets short. The model results, under suitable restrictions of the parameters of the model, in partial consumption insurance in equilibrium. With log-utility and idiosyncratic income shocks taking two values one of which is zero (e.g., employment and unemployment) we show that the equilibrium can …

A New City For A New Era: Xiong'an As Showcase Of China's Evolving Urban Ideology, Andrew Stokols

Research Collection College of Integrative Studies

Cities have long been expressions of political ideology in China and elsewhere. During China’s rapid urbanization over the past few decades, “new areas” became popular strategies to promote urban growth, following the success of Shenzhen, widely regarded as China’s first special economic zone. Today under Xi, Xiong’an New Area has become the latest “new area of national significance.” But unlike previous new areas in China, Xiong’an has become wedded to a distinct vision of the urban in Xi Jinping’s China, one in which the excesses of reform-era urbanization are controlled through new forms of affordable housing and finance, new ecological …

Breaking The Reasoning Barrier: A Survey On Llm Complex Reasoning Through The Lens Of Self-Evolution, Tao He, Hao Li, Jingchang Chen, Runxuan Liu, Yixin Cao, Lizi Liao, Zihao Zheng, Zheng Chu, Jiafeng Liang, Ming Liu, Bing Qin

Research Collection School Of Computing and Information Systems

The release of OpenAI’s O1 and subsequent projects like DeepSeek R1 has significantly advanced research on complex reasoning in LLMs. This paper systematically analyzes existing reasoning studies from the perspective of self-evolution, structured into three components: data evolution, model evolution, and self-evolution. Data evolution explores methods to generate higher-quality reasoning training data. Model evolution focuses on training strategies to boost reasoning capabilities. Self-evolution research autonomous system evolution via iterating cycles of data and model evolution. We further discuss the scaling law of self-evolution and analyze representative O1-like works through this lens. By summarizing advanced methods and outlining future directions, this …

Simulating Before Planning: Constructing Intrinsic User World Model For User-Tailored Dialogue Policy Planning, Tao He, Lizi Liao, Ming Liu, Bing Qin

Research Collection School Of Computing and Information Systems

Recent advancements in dialogue policy planning have focused on optimizing system agent policies to achieve predefined goals, emphasizing strategy design, trajectory acquisition, and training efficiency. However, these approaches often overlook the critical role of user characteristics, which are essential in real-world scenarios like conversational search and recommendation, where interactions must adapt to individual user traits such as personality, preferences, and goals. To address this gap, we conduct a comprehensive study using task-specific user personas to evaluate dialogue policy planning under diverse user behaviors. Our analysis, based on these user profiles, reveals significant shortcomings in existing approaches, underscoring the necessity for …

Machine Learning For Digital Biomarker-Based Detection Of Cognitive Decline, Seng Khoon The

Dissertations and Theses Collection (Open Access)

Dementia is a neurodegenerative disease with a prevalence rate expected to triple by 2050, posing a significant challenge for health services. To impede the increasing prevalence, medical professionals and scientists are actively investigating technology to detect cognitive decline at a reversible stage known as Mild Cognitive Impairment (MCI). Digital biomarker technology is an emerging pragmatic approach to permit objective, ecologically valid, and long-term continuous measurement of cognitive health status, rendering it as one of the promising technologies for early MCI detection. Despite its potential, it is nontrivial to encode, extract and combine predictive information from these digital biomarker technologies; advanced …

Enhancing Graph Representation Learning Through Self-Supervision: An Augmentation Perspective, Jianyuan Bo

Dissertations and Theses Collection (Open Access)

Graph representation learning has become fundamental in various domains, from social networks to molecular structures, enabling extraction of meaningful patterns from graph-structured data. While deep learning approaches, particularly graph neural networks, have shown promising results, their effectiveness is often limited by the scarcity of labeled data. This challenge is particularly acute in graph domains where annotation requires specialized expertise and is prohibitively expensive. Self-supervised learning has emerged as a promising direction to address this limitation by creating auxiliary tasks from unlabeled data, with augmentation strategies playing a crucial role in their success.

Current graph self-supervised learning methods face several critical …

Analyzing Google Maps As A Data Source For Urban Research In Dhaka, Xinyi Du

Dissertations and Theses Collection (Open Access)

This paper investigates how mass transit infrastructure shapes urban economic activity by examining the impact of Dhaka's first metro line using novel Google Maps data. Leveraging the opening of Metro Line 6 on December 2022, we employ a difference-in-differences framework to analyze changes in business establishment density around metro stations. Our estimates show that every 1% reduction in distance to the nearest metro station adds, on average, about 0.092–0.111 establishments per 40 m × 40 m grid cell—that is, roughly 57 – 69 additional businesses per square kilometer. The effect is even more pronounced for dining: about 1 – 4 …