Digital Commons Network^™

Large Language Models As End-To-End Combinatorial Optimization Solvers, Xia Jiang, Yaoxin Wu, Minshuo Li, Zhiguang Cao, Yingqian Zhang

Research Collection School Of Computing and Information Systems

Combinatorial optimization (CO) problems, central to decision-making scenarios like logistics and manufacturing, are traditionally solved using problem-specific algorithms requiring significant domain expertise. While large language models (LLMs) have shown promise in automating CO problem solving, existing approaches rely on intermediate steps such as code generation or solver invocation, limiting their generality and accessibility. This paper introduces a novel framework that empowers LLMs to serve as end-to-end CO solvers by directly mapping natural language problem descriptions to solutions. We propose a two-stage training strategy: supervised fine-tuning (SFT) imparts LLMs with solution generation patterns from domain-specific solvers, while a feasibility-and-optimality-aware reinforcement learning …

Do Code Semantics Help? A Comprehensive Study On Execution Trace-Based Information For Code Large Language Models, Jian Wang, Xiaofei Xie, Qiang Hu, Shangqing Liu, Yi Li

Research Collection School Of Computing and Information Systems

Code Large Language Models (Code LLMs) have opened a new era in programming with their impressive capabilities. However, recent research has revealed critical limitations in their ability to reason about runtime behavior and understand the actual functionality of programs, which poses significant challenges for their post-training and practical deployment. Specifically, Code LLMs encounter two principal issues: (1) a lack of proficiency in reasoning about program execution behavior, as they struggle to interpret what programs actually do during runtime, and (2) inconsistent and fragmented representation of semantic information, such as execution traces, across existing methods, which hinders their ability to generalize …

Explainable Sentiment Analysis With Deepseek-R1: Performance, Efficiency, And Few-Shot Learning, Donghao Huang, Zhaoxia Wang

Research Collection School Of Computing and Information Systems

Large language models (LLMs) have transformed sentiment analysis, yet balancing accuracy, efficiency, and explainability remains a critical challenge. This study presents the first comprehensive evaluation of DeepSeek-R1—an open-source reasoning model—against OpenAI’s GPT-4o and GPT-4o-mini. We test the full 671B model and its distilled variants, systematically documenting few-shot learning curves. Our experiments show DeepSeek-R1 achieves a 91.39% F1 score on 5-class sentiment and 99.31% accuracy on binary tasks with just 5 shots, an eightfold improvement in few-shot efficiency over GPT-4o. Architecture-specific distillation effects emerge, where a 32B Qwen2.5-based model outperforms the 70B Llama-based variant by 6.69 percentage points. While its reasoning …

Efficient Integration Of External Knowledge To Llm-Based World Models Via Retrieval-Augmented Generation And Reinforcement Learning, Chang Yang, Xinrun Wang, Qinggang Zhang, Qi Jiang, Xiao Huang

Research Collection School Of Computing and Information Systems

World models achieve remarkable success in predicting future states and planning in complex environments and Large Language Models (LLMs) serve as promising foundation to build general world models. However, their performances are usually constrained by the limited external knowledge to specific environments. Existing research attempts to enhance LLM-based world models through prompting or fine-tuning approaches, which are either requiring human knowledge or computationally extensive. Therefore, we introduce Retrieval-Augmented World Models (RAWM), a novel framework that leverages retrieval-augmented generation to efficiently integrate the external knowledge to LLM-based world models. Our main contributions are threefold: (i) We introduce a memory system and …

One Planner To Guide Them All! Learning Adaptive Conversational Planners For Goal-Oriented Dialogues, Huy Dao, Lizi Liao

Research Collection School Of Computing and Information Systems

Goal-oriented dialogues, such as recommendation and negotiation, often require balancing multiple, conflicting objectives. Existing methods typically involve training separate models for specific combinations of objectives, leading to computational and scalability issues. In this work, we aim to develop a new dialogue policy method that can adapt to varying objective preferences at inference time without retraining. This raises several challenges in terms of both (1) optimization strategy and (2) knowledge utilization. To address these, we propose a novel learning framework, Preference Adaptive Dialogue Policy Planner (PADPP), for multi-objective goal-oriented dialogues. Specifically, to tackle the former, we introduce a novel policy optimization …

Singapore Awakened: How Success – And Flourishing – Shape Family, Seow Hon Tan

Research Collection Yong Pung How School Of Law

Assoc. Prof. (Dr.) Tan Seow Hon delivered the keynote address at Cultivate SG’s second annual conference, “Unfiltered – The Family on Trial”, on 17 November 2025. In her speech titled “Singapore Awakened: How Success – and the Alternative of Flourishing – Shape Family”, Dr Tan reflects on the “Singapore Dream”, the narrow mindset of success in contrast with the concept of flourishing, and how these impact marriage and family. She concludes by offering some thoughts on how to move from success to flourishing.

Interpersonal Capacity For Trustworthiness: A Reflective Framework For Navigating Entrustment, Roberto Angelo Moreira Vale

Dissertations and Theses Collection (Open Access)

This dissertation advances understanding of how trust shapes salient cross-cultural encounters, drawing on a constructivist grounded theory analysis of 220 interview accounts. Across these narratives, trust-related dynamics consistently appeared alongside 16 other contextual, interpersonal, and intrapersonal factors. Notably, these dynamics were identified in interviews with participants from all GLOBE cultural clusters, suggesting a degree of cross-cultural breadth that warrants further empirical testing. Together, these patterns indicate that it is not cultural difference alone that makes an encounter meaningful, but how individuals interpret and respond to the possibility or risk of entrusting and being entrusted. Salience emerged at moments when participants …

How Behavioral Science Can Improve The Return On Ai Investments, David De Cremer, Shane Schweitzer, Jack Mcguire, Devesh Narayanan

Research Collection Lee Kong Chian School Of Business

Many AI projects fail because leaders treat adoption as a tech purchase instead of a behavioral change problem. People resist tools that disrupt routines, overreact to visible AI errors, and prefer familiar human judgment. As a result, even good systems fail to gain purchase. Leaders can address this problem by applying “Behavioral Human-Centered AI” across the AI adoption cycle. In the design phrase, companies should co-design with diverse users, add purposeful friction where it improves scrutiny, require beta tests with subgroup results and behavioral input. During adoption, they should frame AI as an augmenter, disclose limits and safeguards, use explainability …

Seeing Culture: A Benchmark For Visual Reasoning And Grounding, Burak Satar, Zhixin Ma, Patrick Amadeus Irrawan, Wilfried Ariel Mulyawan, Jing Jiang, Ee-Peng Lim, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

Multimodal vision-language models (VLMs) have made substantial progress in various tasks that require a combined understanding of visual and textual content, particularly in cultural understanding tasks, with the emergence of new cultural datasets. However, these datasets frequently fall short of providing cultural reasoning while underrepresenting many cultures.In this paper, we introduce the Seeing Culture Benchmark (SCB), focusing on cultural reasoning with a novel approach that requires VLMs to reason on culturally rich images in two stages: i) selecting the correct visual option with multiple-choice visual question answering (VQA), and ii) segmenting the relevant cultural artifact as evidence of reasoning. Visual …

From Personas To Talks: Revisiting The Impact Of Personas On Llm-Synthesized Emotional Support Conversations, Shenghan Wu, Yimo Zhu, Wynne Hsu, Mong-Li Lee, Yang Deng

Research Collection School Of Computing and Information Systems

The rapid advancement of Large Language Models (LLMs) has revolutionized the generation of emotional support conversations (ESC), offering scalable solutions with reduced costs and enhanced data privacy. This paper explores the role of personas in the creation of ESC by LLMs. Our research utilizes established psychological frameworks to measure and infuse persona traits into LLMs, which then generate dialogues in the emotional support scenario. We conduct extensive evaluations to understand the stability of persona traits in dialogues, examining shifts in traits post-generation and their impact on dialogue quality and strategy distribution. Experimental results reveal several notable findings: 1) LLMs can …

Adasteer: Your Aligned Llm Is Inherently An Adaptive Jailbreak Defender, Weixiang Zhao, Jiahe Guo, Yulin Hu, Yang Deng, An Zhang, Xingyu Sui, Xinyang Han, Yanyan Zhao, Bing Qin, Tat-Seng Chua, Ting Liu

Research Collection School Of Computing and Information Systems

Despite extensive efforts in safety alignment, large language models (LLMs) remain vulnerable to jailbreak attacks. Activation steering offers a training-free defense method but relies on fixed steering coefficients, resulting in suboptimal protection and increased false rejections of benign inputs. To address this, we propose AdaSteer, an adaptive activation steering method that dynamically adjusts model behavior based on input characteristics. We identify two key properties: Rejection Law (R-Law), which shows that stronger steering is needed for jailbreak inputs opposing the rejection direction, and Harmfulness Law (H-Law), which differentiates adversarial and benign inputs. AdaSteer steers input representations along both the Rejection Direction …

Chain Of Strategy Optimization Makes Large Language Models Better Emotional Supporter, Weixiang Zhao, Xingyu Sui, Xinyang Han, Yang Deng, Yulin Hu, Jiahe Guo, Libo Qin, Qianyun Du, Shijin Wang, Yanyan Zhao, Bing Qin, Ting Liu

Research Collection School Of Computing and Information Systems

The growing emotional stress in modern society has increased the demand for Emotional Support Conversations (ESC). While Large Language Models (LLMs) show promise for ESC, they face two key challenges: (1) low strategy selection accuracy, and (2) preference bias, limiting their adaptability to users’ emotional needs. Existing supervised fine-tuning (SFT) struggles to address these issues, as it rigidly trains models on single gold-standard responses without modeling nuanced strategy trade-offs. To overcome these limitations, we propose a novel two-stage framework that optimizes strategy selection preferences at each dialogue turn. We first leverage Monte Carlo Tree Search to construct ESC-Pro, a high-quality …

Exploring Autonomous Agents: A Closer Look At Why They Fail When Completing Tasks, Ruofan Lu, Yichen Li, Yintong Huo

Research Collection School Of Computing and Information Systems

Autonomous agent systems powered by Large Language Models (LLMs) have demonstrated promising capabilities in automating complex tasks. However, current evaluations largely rely on success rates without systematically analyzing the interactions, communication mechanisms, and failure causes within these systems. To bridge this gap, we present a benchmark of 34 representative programmable tasks designed to rigorously assess autonomous agents. Using this benchmark, we evaluate three popular open-source agent frameworks combined with two LLM backbones, observing a task completion rate of approximately 50%. Through in-depth failure analysis, we develop a three-tier taxonomy of failure causes aligned with task phases, highlighting planning errors, task …

Envisioning Future Interactive Web Development: Editing Webpage With Natural Language, Truong Hai Dang, Jingyu Xiao, Yintong Huo

Research Collection School Of Computing and Information Systems

The evolution of web applications relies on iterative code modifications, a process that is traditionally manual and time-consuming. While Large Language Models (LLMs) can generate UI code, their ability to edit existing code from new design requirements (e.g., ”center the logo”) remains a challenge. This is largely due to the absence of large-scale, high-quality tuning data to align model performance with human expectations. In this paper, we introduce a novel, automated data generation pipeline that uses LLMs to synthesize a high-quality fine-tuning dataset for web editing, named Instruct4Edit. Our approach generates diverse instructions, applies the corresponding code modifications, and performs …

Context-Aware Hierarchical Taxonomy Generation For Scientific Papers Via Llm-Guided Multi-Aspect Clustering, Kun Zhu, Lizi Liao, Yuxuan Gu, Lei Huang, Xiaocheng Feng, Bing Qin

Research Collection School Of Computing and Information Systems

The rapid growth of scientific literature demands efficient methods to organize and synthesize research findings. Existing taxonomy construction methods, leveraging unsupervised clustering or direct prompting of large language models (LLMs), often lack coherence and granularity. We propose a novel context-aware hierarchical taxonomy generation framework that integrates LLM-guided multi-aspect encoding with dynamic clustering. Our method leverages LLMs to identify key aspects of each paper (e.g., methodology, dataset, evaluation) and generates aspect-specific paper summaries, which are then encoded and clustered along each aspect to form a coherent hierarchy. In addition, we introduce a new evaluation benchmark of 156 expert-crafted taxonomies encompassing 11.6k …

Why Stop At One Error? Benchmarking Llms As Data Science Code Debuggers For Multi-Hop And Multi-Bug Errors, Zhiyu Yang, Shuo Wang, Yukun Yan, Yang Deng

Research Collection School Of Computing and Information Systems

LLMs are transforming software development, yet current code generation and code repair benchmarks mainly assess syntactic and functional correctness in simple, single-error cases. LLMs’ capabilities to autonomously find and fix runtime logical errors in complex data science code remain largely unexplored. To address this gap, we introduce DSDBench: the Data Science Debugging Benchmark, the first benchmark for systematic evaluation of LLMs on multi-hop error tracing and multi-bug detection in data science code debugging. DSDBench adapts datasets from existing data science task benchmarks, such as DABench and MatPlotBench, featuring realistic data science debugging tasks with automatically synthesized multi-hop, multi-bug code snippets. …

Discussion Of "Csr And Negative Corporate Events: The Moderating Role Of Managerial Overconfidence", Hye Sun Chang

Research Collection School Of Accountancy

Corporate social responsibility (CSR) refers to the notion that firms are accountable not only to shareholders but also to a broader set of stakeholders including customers, employees, creditors, and the communities in which they operate. Although CSR has long been part of corporate discourse, its prominence has grown with the rise of environmental, social, and governance (ESG) concerns. Today’s consumers and stakeholders are increasingly attentive to issues such as climate change, economic inequality, labor rights, and social justice, prompting firms to align their strategies with evolving societal expectations. Building on this increasingly salient backdrop, Chu et al. (2026), hereafter CCT, …

Generative Ai And Empirical Software Engineering: A Paradigm Shift, Christoph Treude, Margaret-Anne Storey

Research Collection School Of Computing and Information Systems

The widespread adoption of generative AI in software engineering marks a paradigm shift, offering new opportunities to design and utilize software engineering tools while influencing both developers and the artifacts they create. Traditional empirical methods in software engineering, including quantitative, qualitative, and mixed-method approaches, are well established. However, this paradigm shift introduces novel data types and redefines many concepts in the software engineering process. The roles of developers, users, agents, and researchers increasingly overlap, blurring the distinctions between these social and technical actors within the field. This paper examines how integrating AI into software engineering challenges traditional research paradigms. It …

Mmlu-Prox: A Multilingual Benchmark For Advanced Large Language Model Evaluation, Weihao Xuan, Et. Al.

Research Collection School Of Computing and Information Systems

Existing large language model (LLM) evaluation benchmarks primarily focus on English, while current multilingual tasks lack parallel questions that specifically assess cross-lingual reasoning abilities. This dual limitation makes it challenging to assess LLMs’ performance in the multilingual setting comprehensively. To fill this gap, we introduce MMLU-ProX, a comprehensive benchmark covering 29 languages, built on an English benchmark. Each language version consists of 11,829 identical questions, enabling direct cross-lingual comparisons. Additionally, to meet efficient evaluation needs, we provide a lite version containing 658 questions per language. To ensure the high quality of MMLU-ProX, we employ a rigorous development process that involves …

Interaction2code: Benchmarking Mllm-Based Interactive Webpage Code Generation From Interactive Prototyping, Jingyu Xiao, Yuxuan Wan, Yintong Huo, Zixin Wang, Xinyi Xu, Wenxuan Wang, Zhiyao Xu, Yuhang Wang, Michael R. Lyu

Research Collection School Of Computing and Information Systems

Multimodal Large Language Models (MLLMs) have demonstrated remarkable performance on the design-to-code task, i.e., generating UI code from UI mock-ups. However, existing benchmarks only contain static web pages for evaluation and ignore the dynamic interaction, limiting the practicality, usability and user engagement of the generated webpages. To bridge these gaps, we present the first systematic investigation of MLLMs in generating interactive webpages. Specifically, we formulate the Interaction-to-Code task and establish the Interaction2Code benchmark, encompassing 127 unique webpages and 374 distinct interactions across 15 webpage types and 31 interaction categories. Through comprehensive experiments utilizing state-of-theart (SOTA) MLLMs, evaluated via both automatic …

Intentionframe: A Semi-Structured, Multi-Aspect Framework For Fine-Grained Conversational Intention Understanding, Zailong Tian, Zhuoheng Han, Lizi Liao, Lizi Liao

Research Collection School Of Computing and Information Systems

Understanding user intentions in multi-turn dialogues is critical for conversational AI, yet existing approaches—relying on rigid slot-value structures or unstructured free-text—fail to fully capture conversational complexity. In this paper, we propose IntentionFrame, a semi-structured framework inspired by psychological and cognitive intention theories, which organizes conversational intents into four interrelated aspects: situation, emotion, action, and knowledge. This design not only retains interpretability but also provides LLMs with a rich context to accurately parse and respond to nuanced user inputs. To efficiently scale IntentionFrame annotations, we introduce a Weakly-supervised Reinforced Generation (WeRG) method that leverages a small set of high-quality human annotations …

Distillcaps: Enhancing Audio-Language Alignment In Captioning Via Retrieval-Augmented Knowledge Distillation, Thinh Pham, Nghiem Diep, Lizi Liao, Binh Nguyen

Research Collection School Of Computing and Information Systems

Automated audio captioning (AAC) benefits from incorporatingexternal context to interpret complex sounds, but doing so withretrieval-augmented generation (RAG) at inference is sometimesinfeasible due to data availability or incurs significant latency andcomplexity. We propose DistillCaps, a novel training-time frame-work that leverages RAG to guide knowledge distillation for im-proved audio-language alignment, while lessening the relianceon retrieval during inference. In our framework, a RAG-equippedteacher model retrieves relevant textual information (e.g., simi-lar captions) for each audio clip and uses it for training to gener-ate context-enriched captions. Simultaneously, a student model istrained to imitate this teacher, learning to produce high-qualitycaptions from audio alone. We further …

Instructors’ Strategies In Creating And Implementing Constructivist Llm-Based Learning Activities, Emily Aurelia, Shun Yi Yeo, Michelle Lui, Effie Lai-Chong Law, Anthony Tang

Research Collection School Of Computing and Information Systems

Large language models (LLMs) are increasingly being integrated into educational settings, enabling more adoption of constructivist teaching and learning approaches in classrooms. This paper explores the strategies instructors are currently using to incorporate LLMs into learning activities that align with constructivist principles, which emphasize that learners actively construct their own knowledge. Through interviews with nine instructors who have designed eleven distinct LLM-based activities and using reflexive thematic analysis, this study identifies various types of learning activities with respect to four different aspects of the constructivist learning theory. The strategies employed and challenges faced to foster constructivist student-LLM interaction were also …

Parameter-Efficient Variational Autoencoder For Multimodal Multi-Interest Recommendation, Nhu Thuat Tran, Hady Wirawan Lauw

Research Collection School Of Computing and Information Systems

Learning user preferences in recommendation systems is enriched by multimodal features, such as textual and visual content, and amplified by multi-interest modeling with Variational AutoEncoders (VAEs). However, prior efforts are limited by single modality focus and cumbersome, parameter-heavy architecture designs. To address these limitations, we introduce an innovative solution that blends the semantic richness of multimodal data with the representational power of multi-representation VAEs. Drawing inspiration from Mixture of Experts (MoE), we cast each VAE as an expert tailored to a specific modality, then fuse them via a novel parameter-merging function into a lean, unified model. This approach efficiently captures …

Memad: Structured Memory Of Debates For Enhanced Multi-Agent Reasoning, Shuai Ling, Lizi Liao, Dongmei Jiang, Weili Guan

Research Collection School Of Computing and Information Systems

Large Language Models (LLMs) demonstrate remarkable in-context learning capabilities but often struggle with complex, multi-step reasoning. Multi-Agent Debate (MAD) frameworks partially address these limitations by enabling iterative agent interactions. However, they neglect valuable historical insights by treating each new debate independently. In this paper, we propose Memory-Augmented MAD (MeMAD), a parameter-free memory-augmented MAD framework that systematically organizes and reuses past debate transcripts. MeMAD stores structured representations of successful and unsuccessful reasoning attempts enriched with self-reflections and peer feedback. It systematically retrieves them via semantic similarity at inference time to inform new reasoning tasks. Our experiments on challenging mathematical reasoning, scientific …

Factors Influencing Consumers’ Online Purchase Decisions: Evidence From Amazon.Com, Weiwei Li

Dissertations and Theses Collection (Open Access)

With the rapid expansion of cross-border e-commerce, platform sellers increasingly adopt diverse price formatsto influence consumer decision-making. In this context, consumers’ perceptions of and responses to price information have become a pivotal issue in understanding online purchase behavior. Using Amazon as the research setting, this study employs a dynamic panel model with monthly product-level data spanning January 2024 to June 2025 to investigate how different price formats—such as Prime-exclusive pricing and coupon mechanisms—affect consumers’ online purchase intentions when the out-ofpocket price is held constant. Furthermore, the moderating effect of promotional events is systematically examined.

Departing from prior research that largely …

Look Before You Decide: Prompting Active Deduction Of Mllms For Assumptive Reasoning, Yian Li, Wentao Tian, Yang Jiao, Jingjing Chen, Tianwen Qian, Bin Zhu, Na Zhao, Yu‑Gang Jiang

Research Collection School Of Computing and Information Systems

Recently, Multimodal Large Language Models (MLLMs) have achieved significant success across multiple disciplines due to their exceptional instruction-following capabilities and extensive world knowledge. However, whether these MLLMs possess human-like compositional reasoning abilities remains an open problem. To unveil their reasoning behaviors, we first curate a Multimodal Assumptive Reasoning Benchmark (MARS-Bench) in this paper. Interestingly, we find that most prevalent MLLMs can be easily fooled by the introduction of a presupposition into the question, whereas such presuppositions appear naive to human reasoning. Besides, we also propose a simple yet effective method, Active Deduction (AD), a novel reinforcement learning paradigm to encourage …

Viewsrd: 3d Visual Grounding Via Structured Multi-View Decomposition, Ronggang Huang, Haoxin Yang, Yan Cai, Xuemiao Xu, Huaidong Zhang, Shengfeng He

Research Collection School Of Computing and Information Systems

3Dvisual grounding aims to identify and localize objects in a 3Dspacebasedontextualdescriptions. However, existing methods struggle with disentangling targets from anchors in complex multi-anchor queries and resolving inconsisten cies in spatial descriptions caused by perspective variations. To tackle these challenges, we propose ViewSRD, a frame work that formulates 3D visual grounding as a structured multi-view decomposition process. First, the Simple Rela tion Decoupling (SRD) module restructures complex multi anchor queries into a set of targeted single-anchor state ments, generating a structured set of perspective-aware de scriptions that clarify positional relationships. These de composed representations serve as the foundation for the Multi-view …

Visual-Enhanced Multimodal Framework For Flexible Job Shop Scheduling Problem, Peng Zhao, Zhiguang Cao, Di Wang, Wen Song, Wei Pang, You Zhou, Yuan Jiang

Research Collection School Of Computing and Information Systems

Multimodal models leverage complementary information across modalities to enrich feature representations. While visual information shows potential in representing structure for some combinatorial optimization problems (COPs), its application to complex scheduling like the Flexible Job Shop Scheduling Problem (FJSP) remains underexplored. Current learning-based FJSP solvers predominantly rely on handcrafted state features. This dependence can lead to inconsistencies and may not fully capture the problem's intricate dynamics. Crucially, these methods overlook visual modalities. Visual representations offer a distinct advantage by inherently capturing the global topological structure and complex resource interactions within the FJSP state. Unlike localized handcrafted features, this holistic, structural view …

Art4math: Handwritten Mathematical Expression Recognition Via Multimodal Sketch Grounding, Yang Zhou, Jin Wang, Yuxiao Zhang, Kaixiang Huang, Guodong Lu, Jingru Yang, Shengfeng He

Research Collection School Of Computing and Information Systems

Handwritten Mathematical Expression Recognition (HMER) remains a challenging task due to the structural complexity of mathematical notation and the ambiguity of handwritten symbols-e.g., ''ρ'' vs. ''p'' or ''B'' vs. ''β''. While stroke-based models offer disambiguation via temporal cues, most existing methods are constrained by coarse modality fusion and a lack of fine-grained cross-modal alignment, further hindered by limited annotated data. We introduce Art for Math (Art4Math), a novel framework that leverages the structural richness of human sketches to enhance HMER through fine-grained, modality-aware learning. Art4Math follows a two-stage training paradigm: Art Grounding (A-Grd) and Math Decoding (M-Dec). In A-Grd, the …