Open Access. Powered by Scholars. Published by Universities.®

Digital Commons Network™

Open Access. Powered by Scholars. Published by Universities.®

Singapore Management University

Discipline
Keyword
Publication Year
Publication
Publication Type

Articles 271 - 300 of 8668

Full-Text Articles in Entire DC Network

Cssa-Fusion: Channel Selective And Spatial Alignment Infrared-Visible Image Fusion, Zhen Li, Zhi Zeng, Zhongrui Xiao, Ming Wen, Zhiyuan Zhang, Yibin Tian Dec 2025

Cssa-Fusion: Channel Selective And Spatial Alignment Infrared-Visible Image Fusion, Zhen Li, Zhi Zeng, Zhongrui Xiao, Ming Wen, Zhiyuan Zhang, Yibin Tian

Research Collection School Of Computing and Information Systems

Infrared-visible image fusion aims to integrate complementary information from two modalities to generate images with enriched semantic content. However, existing methods often neglect two critical aspects: the design of a local–global feature enhancement architecture and spatial alignment. To address these challenges, we propose Channel Selective and Spatial Alignment Fusion (CSSA-Fusion), a novel framework composed of two synergistic modules. The first is a selective channel and redundancy suppression module, which introduces a dual-branch selective channel attention mechanism to jointly capture local saliency and global channel importance for enhanced feature representation, and an informativeness–redundancy separation strategy to suppress redundant information while preserving …

Go to article

A Partition Cover Approach To Tokenization, Jia Peng Lim, Shawn Tan, Davin Choo, Hady Wirawan Lauw Dec 2025

A Partition Cover Approach To Tokenization, Jia Peng Lim, Shawn Tan, Davin Choo, Hady Wirawan Lauw

Research Collection School Of Computing and Information Systems

Tokenization is the process of encoding strings into tokens of a fixed vocabulary size, and is widely utilized in Natural Language Processing applications. The leading tokenization algorithm today is Byte Pair Encoding (BPE), which formulates the tokenization problem as a compression problem and tackles it by performing sequences of merges. In this work, we formulate tokenization as an optimization objective, show that it is NP-hard via a simple reduction from vertex cover, and propose a polynomial-time greedy algorithm GreedTok. Our formulation naturally relaxes to the well-studied weighted maximum coverage problem which has a simple -approximation algorithm GreedWMC. Through empirical evaluations …

Go to article

Sheetpedia: A 300k-Spreadsheet Corpus For Spreadsheet Intelligence And Llm Fine-Tuning, Zailong Tian, Zhuoheng Han, Houfeng Wang, Lizi Liao Dec 2025

Sheetpedia: A 300k-Spreadsheet Corpus For Spreadsheet Intelligence And Llm Fine-Tuning, Zailong Tian, Zhuoheng Han, Houfeng Wang, Lizi Liao

Research Collection School Of Computing and Information Systems

Spreadsheets are widely used for data analysis and reporting, yet their complex structure and formula logic pose significant challenges for AI systems. We introduce Sheetpedia, a large-scale corpus of over 290,000 diverse spreadsheets (from 324,000+ workbooks) compiled from enterprise email archives and online forums. We detail a rigorous collection and preprocessing pipeline (integrating the Enron email spreadsheet archive and the Fuse web corpus, plus a new crawl of Excel forums) to standardize formats, filter languages, and remove duplicates. Sheetpedia provides extensive coverage of real formulas and annotations – addressing a gap left by prior table datasets (e.g. web tables used …

Go to article

Contx: Scene Context Prediction Via Context Bank And Layout Perception, Jingxin Liang, Yangyang Xu, Haorui Song, Yuan Lu, Yuhui Deng, Yiyi Long, Yan Huang, Shengxin Liu, Jianbo Jiao, Shengfeng He Dec 2025

Contx: Scene Context Prediction Via Context Bank And Layout Perception, Jingxin Liang, Yangyang Xu, Haorui Song, Yuan Lu, Yuhui Deng, Yiyi Long, Yan Huang, Shengxin Liu, Jianbo Jiao, Shengfeng He

Research Collection School Of Computing and Information Systems

Scene context prediction, which seeks to infer unknown contextual information from isolated object properties, currently faces limitations due to predominant reliance on pixel-wise supervision that overlooks real-world context priors. To address this, we present ContX, a context-prior-driven, coarse-to-fine model. ContX distinctively integrates explicit linguistic-contextual knowledge in two key ways. First, it proposes a linguistic guided context bank, leveraging linguistic-statistical contextual data to guide the rationality of segmentation shapes and foster meaningful inter-class contextual interactions. Second, ContX augments contextual comprehension by correlating layouts with linguistic descriptions, enhancing layout perception through a multi-modal strategy. Comprehensive experiments demonstrate ContX's superiority and versatility, outperforming …

Go to article

Backdoorllm: A Comprehensive Benchmark For Backdoor Attacks And Defenses On Large Language Models, Yige Li, Hanxun Huang, Yunhan Zhao, Xingjun Ma, Jun Sun Dec 2025

Backdoorllm: A Comprehensive Benchmark For Backdoor Attacks And Defenses On Large Language Models, Yige Li, Hanxun Huang, Yunhan Zhao, Xingjun Ma, Jun Sun

Research Collection School Of Computing and Information Systems

Generative large language models (LLMs) have achieved state-of-the-art results on a wide range of tasks, yet they remain susceptible to backdoor attacks: carefully crafted triggers in the input can manipulate the model to produce adversaryspecified outputs. While prior research has predominantly focused on backdoor risks in vision and classification settings, the vulnerability of LLMs in open-ended text generation remains underexplored. To fill this gap, we introduce BackdoorLLM1 , the first comprehensive benchmark for systematically evaluating backdoor threats in text-generation LLMs. BackdoorLLM provides: (i) a unified repository of benchmarks with a standardized training and evaluation pipeline; (ii) a diverse suite of …

Go to article

Griffin: Effective Token Alignment For Faster Speculative Decoding, Shijing Hu, Jingyang Li, Xingyu Xie, Zhihui Lu, Kim-Chuan Toh, Pan Zhou Dec 2025

Griffin: Effective Token Alignment For Faster Speculative Decoding, Shijing Hu, Jingyang Li, Xingyu Xie, Zhihui Lu, Kim-Chuan Toh, Pan Zhou

Research Collection School Of Computing and Information Systems

Speculative decoding accelerates inference in large language models (LLMs) by generating multiple draft tokens simultaneously. However, existing methods often struggle with token misalignment between the training and decoding phases, limiting their performance. To address this, we propose GRIFFIN, a novel framework that incorporates a token-alignable training strategy and a token-alignable draft model to mitigate misalignment. The training strategy employs a loss masking mechanism to exclude highly misaligned tokens during training, preventing them from negatively impacting the draft model’s optimization. The token-alignable draft model introduces input tokens to correct inconsistencies in generated features. Experiments on LLaMA, Vicuna, Qwen and Mixtral models …

Go to article

Large Language Models As End-To-End Combinatorial Optimization Solvers, Xia Jiang, Yaoxin Wu, Minshuo Li, Zhiguang Cao, Yingqian Zhang Dec 2025

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 …

Go to article

Agentguard: An Active Threat Discovery System For Package Confusion Using Multi-Agent Collaboration, Wei Ma, Yu Li, Zhi Chen, Ye Liu, Lingxiao Jiang, Qiang Hu, Junyi Tao Dec 2025

Agentguard: An Active Threat Discovery System For Package Confusion Using Multi-Agent Collaboration, Wei Ma, Yu Li, Zhi Chen, Ye Liu, Lingxiao Jiang, Qiang Hu, Junyi Tao

Research Collection School Of Computing and Information Systems

The proliferation of open-source software (OSS) has made software supply chains prime targets for attacks like Package Confusion, where adversaries publish malicious packages with names deceptively similar to legitimate ones. Existing detection methods often rely on simple lexical similarity or passive analysis of known package pairs, struggle with high false positive rates (FPR), fail to proactively identify emerging threats, and are vulnerable to adversarial evasion. To overcome these limitations, we introduce AgentGuard, a novel framework for proactive, single-input package confusion detection. AgentGuard employs a multi-agent architecture that autonomously discovers potential confusion targets using fine-tuned word embedding model to hybird semantic …

Go to article

Accuracy-Enabling Differential Privacy-Preserving Truth Discovery, Man Zhang, Xinghua Li, Yinbin Miao, Bin Luo, Siqi Ma, Robert H. Deng Dec 2025

Accuracy-Enabling Differential Privacy-Preserving Truth Discovery, Man Zhang, Xinghua Li, Yinbin Miao, Bin Luo, Siqi Ma, Robert H. Deng

Research Collection School Of Computing and Information Systems

Perturbation-based privacy-preserving truth discovery requires the Service Provider (SP) to calculate the truthful aggregation result from perturbed data of the Data Sources (DSs), which inevitably damages the aggregation accuracy due to perturbation noise added in the data. Thus, the existing works attempt to relieve the perturbation errors by reducing noise amounts or adjusting aggregation weights of DSs. However, the former sacrifices DSs’ privacy preservation and the latter has the limited accuracy recovery performance. Aiming at it, we propose an accuracy-enabling differential privacy-preserving truth discovery consisting of an independence-guaranteed data perturbation module and a progressive-private noise elimination module. Specifically, in the …

Go to article

Fl-Cdf: Collaborative Defense Framework For Backdoor Mitigation In Federated Learning, Haiyan Zhang, Xinghua Li, Yinbin Miao, Shunjie Yuan, Mengyao Zhu, Ximeng Liu, Robert H. Deng Dec 2025

Fl-Cdf: Collaborative Defense Framework For Backdoor Mitigation In Federated Learning, Haiyan Zhang, Xinghua Li, Yinbin Miao, Shunjie Yuan, Mengyao Zhu, Ximeng Liu, Robert H. Deng

Research Collection School Of Computing and Information Systems

Federated learning (FL) is vulnerable to backdoor attacks due to its distributed nature. Existing unilateral defense mechanisms often fail against persistent attack strategies, primarily due to their limited perspectives. To address the challenge of model misclassification on the server side caused by overlooked model similarity drift, and gradient misjudgment on the client side caused by semantic learning imbalances across classes, this paper proposes a collaborative defense framework for federated learning, termed FL-CDF. FL-CDF establishes an end-to-end defense through a bidirectional client-server collaboration mechanism. Specifically: (1) On the client side, an adversarial perturbation-based malicious neuron detection module is introduced. This module …

Go to article

Reliability And Validity Of A Self-Administrated Online Assessment Of Intrinsic Capacity: A Singapore Cohort Study, Paulin Tay Straughan, William Tov, Lay Khoon Lau, Li Ling Grace Cheong, Chong Sheng Micah Tan, William Tov, Yew Yoong Ding, Wee Shiong Lim Dec 2025

Reliability And Validity Of A Self-Administrated Online Assessment Of Intrinsic Capacity: A Singapore Cohort Study, Paulin Tay Straughan, William Tov, Lay Khoon Lau, Li Ling Grace Cheong, Chong Sheng Micah Tan, William Tov, Yew Yoong Ding, Wee Shiong Lim

Research Collection School of Social Sciences

Objective: To ascertain the construct validity and reliability of a self-administered web-based assessment of intrinsic capacity (IC). Design: Cross-sectional data analysis of a prospective cohort study. Settings and Participants: We included data from 6,434 respondents (age, mean (SD): 65.33 (5.81) years; 52.4% women) of the Singapore Life Panel population study who participated in the online surveys in March 2022 and May 2022.MethodsIncremental nested factor structures of IC were modelled with confirmatory factor analysis (CFA) and their goodness-of-fit were assessed mainly with root mean square error of approximation (RMSEA), comparative fit index (CFI), Tucker-Lewis index (TLI), and standardized root mean square …

Go to article

Effectiveness Of Cognitive And Behavioral Interventions In The Treatment Of Schizophrenia: An Umbrella Review Of Meta-Analyses, Gabriel Xing Da Tan, Andree Hartanto, Zoey Khai Yee Eun, Meilan Hu, Kean J. Hsu, Nadyanna M. Majeed Dec 2025

Effectiveness Of Cognitive And Behavioral Interventions In The Treatment Of Schizophrenia: An Umbrella Review Of Meta-Analyses, Gabriel Xing Da Tan, Andree Hartanto, Zoey Khai Yee Eun, Meilan Hu, Kean J. Hsu, Nadyanna M. Majeed

Research Collection School of Social Sciences

Background: Cognitive and behavioral interventions have risen in popularity both as an adjunctive treatment to antipsychotic medication and as an alternative treatment for schizophrenia. With the growing number of such interventions, we performed an umbrella review to provide a comprehensive summary comparing the effectiveness of the different interventions among populations with schizophrenia. Methods: This umbrella review included meta-analyses evaluating cognitive and behavioral interventions for schizophrenia. Following PRISMA guidelines, the initial search yielded 4888 records, and after a three-stage screening procedure, 33 meta-analyses met the inclusion criteria for the final analysis. Results: Our findings from the 33 meta-analyses support the efficacy …

Go to article

Navigating Ai-Nature Frictions: Autonomous Vehicle Testing And Nature-Based Constraints, Prerona Das, Orlando Woods, Lily Kong Dec 2025

Navigating Ai-Nature Frictions: Autonomous Vehicle Testing And Nature-Based Constraints, Prerona Das, Orlando Woods, Lily Kong

Research Collection College of Integrative Studies

In cities, the application of Artificial Intelligence (AI) is being directed towards transforming different aspects of urban life. These applications take material form in urban spaces, with autonomous vehicles (AVs) providing a prominent example. AI systems rely on large volumes of data on their surroundings to refine the algorithms and enhance the accuracy of prediction for operational efficiency and safety. However, such algorithmic learning and execution can present challenges when dealing with the unpredictable, complex, and dynamic aspects of urban spaces. Nature is a paradigmatic example of such unpredictability, because natural phenomena usually defy consistent patterns and precise data-based modelling. …

Go to article

Mando-Llm: Heterogeneous Graph Transformers With Large Language Models For Smart Contract Vulnerability Detection, Nhat Minh Nguyen, Huu Hoang Nguyen, Long Le Thanh, Zahra Ahmadi, Thanh Nam Doan, Daoyuan Wu, Lingxiao Jiang Dec 2025

Mando-Llm: Heterogeneous Graph Transformers With Large Language Models For Smart Contract Vulnerability Detection, Nhat Minh Nguyen, Huu Hoang Nguyen, Long Le Thanh, Zahra Ahmadi, Thanh Nam Doan, Daoyuan Wu, Lingxiao Jiang

Research Collection School Of Computing and Information Systems

Detecting vulnerabilities in smart contracts is vital for the security and reliability of decentralized apps. To facilitate vulnerability detection, contract codes, including bug patterns, are represented as heterogeneous graphs with various nodes and edges, like control-flow and function-call graphs. However, existing graph learning techniques struggle with large, complex graphs. This paper presents MANDO-LLM, a novel framework that combines heterogeneous graph transformers (HGTs) with large language models (LLMs) for detecting vulnerabilities in smart contracts represented as heterogeneous contract graphs built upon control-flow and call graphs. MANDO-LLM uses LLMs to capture code features from control-flow and call data, customizes HGTs to learn …

Go to article

Iostom: Offline Imitation Learning From Observations Via State Transition Occupancy Matching, Quang Anh Pham, Brahmanage Janaka Chathuranga Thilakarathna, Tien Mai, Akshat Kumar Dec 2025

Iostom: Offline Imitation Learning From Observations Via State Transition Occupancy Matching, Quang Anh Pham, Brahmanage Janaka Chathuranga Thilakarathna, Tien Mai, Akshat Kumar

Research Collection School Of Computing and Information Systems

Offline Learning from Observations (LfO) focuses on enabling agents to imitate expert behavior using datasets that contain only expert state trajectories and separate transition data with suboptimal actions. This setting is both practical and critical in real-world scenarios where direct environment interaction or access to expert action labels is costly, risky, or infeasible. Most existing LfO methods attempt to solve this problem through state or state-action occupancy matching. They typically rely on pretraining a discriminator to differentiate between expert and non-expert states, which could introduce errors and instability—especially when the discriminator is poorly trained. While recent discriminator-free methods have emerged, …

Go to article

No Experts, No Problem: Avoidance Learning From Bad Demonstrations, Minh Huy Hoang, Tien Mai, Pradeep Varakantham Dec 2025

No Experts, No Problem: Avoidance Learning From Bad Demonstrations, Minh Huy Hoang, Tien Mai, Pradeep Varakantham

Research Collection School Of Computing and Information Systems

This paper addresses the problem of learning avoidance behavior within the context of offline imitation learning. In contrast to conventional methodologies that prioritize the replication of expert or near-expert demonstrations, our work investigates a setting where expert (or desirable) data is absent, and the objective is to learn to eschew undesirable actions by leveraging demonstrations of such behavior (i.e., learning from negative examples).To address this challenge, we propose a novel training objective grounded in the maximum entropy principle. We further characterize the fundamental properties of this objective function, reformulating the learning process as a cooperative inverse Q-learning task. Moreover, we …

Go to article

Rising From Ashes: Generalized Federated Learning Via Dynamic Parameter Reset, Jiahao Wu, Ming Hu, Yanxin Yang, Xiaofei Xie, Zekai Chen, Chenyu Song, Mingsong Chen Dec 2025

Rising From Ashes: Generalized Federated Learning Via Dynamic Parameter Reset, Jiahao Wu, Ming Hu, Yanxin Yang, Xiaofei Xie, Zekai Chen, Chenyu Song, Mingsong Chen

Research Collection School Of Computing and Information Systems

Although Federated Learning (FL) is promising for privacy-preserving collaborative model training, it suffers from low inference performance due to heterogeneous client data. Due to heterogeneous data across clients, FL training easily learns client-specific overfitting features. Existing FL methods adopt coarsegrained averaging, which can easily cause the global model to get stuck in local optima, leading to poor generalization. Specifically, this paper presents a novel FL framework, FedPhoenix, to address this issue. It stochastically resets partial parameters in each round to destroy some features of the global model, guiding FL training to learn multiple generalized features for inference rather than specific …

Go to article

Generalization Bounds For Rank‑Sparse Neural Networks, Antoine Ledent, Rodrigo Alves, Yunwen Lei Dec 2025

Generalization Bounds For Rank‑Sparse Neural Networks, Antoine Ledent, Rodrigo Alves, Yunwen Lei

Research Collection School Of Computing and Information Systems

It has been recently observed in much of the literature that neural networks exhibit a bottleneck rank property: for larger depths, the activation and weights of neural networks trained with gradient-based methods tend to be of approximately low rank. In fact, the rank of the activations of each layer converges to a fixed value referred to as the “bottleneck rank”, which is the minimum rank required to represent the training data. This perspective is in line with the observation that regularizing linear networks (without activations) with weight decay is equivalent to minimizing the Schatten p quasi norm of the neural …

Go to article

Design Principles For Customer‑Engaging Digital Service Systems: An Action Research Study, Keng Siau, Xiaofeng Chen, Xin Tan Dec 2025

Design Principles For Customer‑Engaging Digital Service Systems: An Action Research Study, Keng Siau, Xiaofeng Chen, Xin Tan

Research Collection School Of Computing and Information Systems

Digital services represent a business approach employed by organizations to operate in the digital environment. However, systematic development guidelines for developing quality digital service systems are lacking in the literature. The authors identified four general challenges for developing and implementing customer-engaging digital service systems (CEDSS). By employing the method of canonical action research in a digital service system project, they derived 10 design principles for developing high-quality CEDSS. They empirically evaluated the design principles in the development project and through follow-up focus group sessions. The design principles provide applicable and actionable guidelines for the development of CEDSS.

Go to article

Bias Testing And Mitigation In Llm-Based Code Generation, Dong Huang, Jie M. Zhang, Qingwen Bu, Xiaofei Xie, Junjie Chen, Heming Cui Dec 2025

Bias Testing And Mitigation In Llm-Based Code Generation, Dong Huang, Jie M. Zhang, Qingwen Bu, Xiaofei Xie, Junjie Chen, Heming Cui

Research Collection School Of Computing and Information Systems

As the adoption of LLMs becomes more widespread in software coding ecosystems, a pressing issue has emerged: does the generated code contain social bias and unfairness, such as those related to age, gender, and race? This issue concerns the integrity, fairness, and ethical foundation of software applications that depend on the code generated by these models but are underexplored in the literature. This paper presents a novel bias testing framework that is specifically designed for code generation tasks. Based on this framework, we conduct an extensive empirical study on the biases in code generated by five widely studied LLMs (i.e., …

Go to article

Genscore: Agent-Based Short-Answer Question Generation And Scoring In Software Engineering Courses, Nguyen Binh Duong Ta, Lwin Khin Shar Dec 2025

Genscore: Agent-Based Short-Answer Question Generation And Scoring In Software Engineering Courses, Nguyen Binh Duong Ta, Lwin Khin Shar

Research Collection School Of Computing and Information Systems

Short-answer questions are commonly used in educational assessments, as they are often viewed as a more effective way than multiple-choice questions to determine whether students have achieved the intended learning outcomes. However, manually creating appropriate questions targeting different cognitive levels such as those defined by the Bloom’s Taxonomy, and grading text answers from students are not trivial tasks for instructors. Existing work on auto-question generation and scoring in computing education typically targets coding-based questions. However, in software engineering courses, assessments can extend beyond coding to understanding of processes, DevOps methodologies, system design, etc. This work aims to address the dual …

Go to article

Constitutional Obiter Dicta On Male-Male Sex And Fundamental Rights In Singapore, Benjamin Joshua Ong Dec 2025

Constitutional Obiter Dicta On Male-Male Sex And Fundamental Rights In Singapore, Benjamin Joshua Ong

Research Collection Yong Pung How School Of Law

The Singapore Court of Appeal held a law prohibiting male–male sexual intercourse (s 377A of the Penal Code) unenforceable on non-rights-based grounds. The court's remarks about the rights to life and liberty (including whether sexual orientation is mutable), freedom of expression, and equality are obiter. But they are significant, since in Singapore, there are few constitutional rights cases and the courts focus on spelling out the limits to executive and legislative power without necessarily striking down exercises of such power on rights grounds. Indeed, the obiter dicta prompted the Legislature to repeal s 377A. Given the repeal, the obiter dicta …

Go to article

Can Limited Partners Mitigate Negative Externalities In Private Equity?, Teodor Duevski, Chhavi Rastogi, Tianhao Yao Nov 2025

Can Limited Partners Mitigate Negative Externalities In Private Equity?, Teodor Duevski, Chhavi Rastogi, Tianhao Yao

Sim Kee Boon Institute for Financial Economics

We show how Limited Partners' (LPs) environmental and social (E&S) concerns transmit to private equity (PE) rms through capital supply. E&S incidents in portfolio companies reduce PE fundraising, as E&S-concerned relationship LPs refrain from recommitting and are not easily substituted. Using a legal reform that expands E&S-concerned public pension capital to PE, we causally show that PE rms internalise LPs' E&S concerns, reducing dirty sector portfolio allocation and increasing ESG hiring. Additionally, PE rms with E&S- concerned relationship LPs engage with portfolio companies to manage E&S risks. Limited capital substitutability enables LPs to delegate E&S preferences, shaping PE allocation and …

Go to article

When Deep Learning Meets Information Retrieval-Based Bug Localization: A Survey, Feifei Niu, Chuanyi Li, Kui Liu, Xin Xia, David Lo Nov 2025

When Deep Learning Meets Information Retrieval-Based Bug Localization: A Survey, Feifei Niu, Chuanyi Li, Kui Liu, Xin Xia, David Lo

Research Collection School Of Computing and Information Systems

Bug localization is a crucial aspect of software maintenance, running through the entire software lifecycle. Information retrieval-based bug localization (IRBL) identifies buggy code based on bug reports, expediting the bug resolution process for developers. Recent years have witnessed significant achievements in IRBL, propelled by the widespread adoption of deep learning (DL). To provide a comprehensive overview of the current state of the art and delve into key issues, we conduct a survey encompassing 61 IRBL studies leveraging DL. We summarize best practices in each phase of the IRBL workflow, undertake a meta-analysis of prior studies, and suggest future research directions. …

Go to article

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 Nov 2025

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 …

Go to article

Explainable Sentiment Analysis With Deepseek-R1: Performance, Efficiency, And Few-Shot Learning, Donghao Huang, Zhaoxia Wang Nov 2025

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 …

Go to article

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 Nov 2025

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 …

Go to article

Local-Thinking Bias, Ed Dehaan, Charles M. C. Lee, Wei Ting Loh Nov 2025

Local-Thinking Bias, Ed Dehaan, Charles M. C. Lee, Wei Ting Loh

Research Collection School Of Accountancy

Local-thinking bias, wherein agents overweight information that comes readily to mind, is a prominent finding in cognitive psychology. In this study, we investigate local-thinking bias in the context of sell-side analysts and measure each analyst’s “local” information as news stemming from their individual coverage portfolio. Tests examining multiple analysts forecasting on the same focal firm at the same time find that individual analysts overweight idiosyncratic local news and underweight news from economically linked firms that are not in their coverage portfolios. Market prices track the analyst bias from local news, leading to predictable and economically significant return reversal patterns in …

Go to article

Unlocking Private Equity Investing, Yin Wang, Steve Balaban Nov 2025

Unlocking Private Equity Investing, Yin Wang, Steve Balaban

Asian Management Insights

Myths and market shifts to take note of.

Go to article

Sustainability And Climate-Related Regulations And Due Diligence, Adolf Peter Nov 2025

Sustainability And Climate-Related Regulations And Due Diligence, Adolf Peter

Asian Management Insights

Why does it matter?

Go to article

First Prev Next Last