Open Access. Powered by Scholars. Published by Universities.®
- Discipline
-
- Physical Sciences and Mathematics (9398)
- Computer Sciences (9090)
- Databases and Information Systems (3572)
- Software Engineering (2227)
- Artificial Intelligence and Robotics (1935)
-
- Social and Behavioral Sciences (1631)
- Business (1308)
- Information Security (1124)
- Numerical Analysis and Scientific Computing (1061)
- Graphics and Human Computer Interfaces (959)
- Engineering (937)
- Theory and Algorithms (513)
- Computer Engineering (471)
- Economics (426)
- Operations Research, Systems Engineering and Industrial Engineering (425)
- Programming Languages and Compilers (413)
- Communication (349)
- OS and Networks (347)
- International and Area Studies (336)
- Asian Studies (327)
- Public Affairs, Public Policy and Public Administration (310)
- Education (296)
- Social Media (271)
- Finance and Financial Management (249)
- Environmental Sciences (240)
- Medicine and Health Sciences (231)
- Transportation (220)
- Econometrics (214)
- Technology and Innovation (201)
- Management Information Systems (188)
- Keyword
-
- Machine learning (149)
- Deep learning (130)
- Artificial intelligence (128)
- Singapore (125)
- Social media (82)
-
- Reinforcement learning (74)
- Privacy (71)
- Data mining (70)
- Security (63)
- Sustainability (61)
- Cloud computing (60)
- Deep Learning (58)
- Optimization (56)
- Empirical study (55)
- Software engineering (55)
- Blockchain (52)
- Natural language processing (52)
- Online learning (52)
- Visualization (52)
- Neural networks (50)
- Task analysis (50)
- Training (50)
- Anomaly detection (49)
- Large Language Models (49)
- Twitter (49)
- Collaboration (47)
- Machine Learning (47)
- Feature extraction (46)
- Algorithms (44)
- Semantics (44)
- Publication Year
- Publication
-
- Research Collection School Of Computing and Information Systems (8597)
- Research Collection Lee Kong Chian School Of Business (428)
- Research Collection School Of Economics (340)
- Dissertations and Theses Collection (Open Access) (275)
- Research Collection School of Social Sciences (193)
-
- Research Collection College of Integrative Studies (138)
- Research Collection Yong Pung How School Of Law (110)
- Research Collection School Of Accountancy (66)
- Asian Management Insights (63)
- Perspectives@SMU (49)
- Dissertations and Theses Collection (20)
- Research Collection Library (19)
- SMU Press Releases and News (18)
- Knowledge@SMU (17)
- FORCE 2026 (14)
- Sim Kee Boon Institute for Financial Economics (14)
- Research@SMU: Connecting the Dots (13)
- Social Space (12)
- MITB Thought Leadership Series (11)
- Research Collection School of Computing and Information Systems (11)
- Oral History Collection (9)
- Report to Stakeholders (9)
- PhD Student’s Publications Collection (8)
- LARC Research Publications (7)
- Research Collection School of Economics (7)
- Student Publications (7)
- Centre for Computational Law (2022-2025) (6)
- CCX Research (5)
- SMU Research Data (4)
- 2024 AI for Research Week (3)
- Publication Type
- File Type
Articles 1891 - 1920 of 10509
Full-Text Articles in Entire DC Network
Vision Paper: Advancing Of Ai Explainability For The Use Of Chatgpt In Government Agencies: Proposal Of A 4-Step Framework, Hui Shan Lee, Shankararaman, Venky, Eng Lieh Ouh
Vision Paper: Advancing Of Ai Explainability For The Use Of Chatgpt In Government Agencies: Proposal Of A 4-Step Framework, Hui Shan Lee, Shankararaman, Venky, Eng Lieh Ouh
Research Collection School Of Computing and Information Systems
This paper explores ChatGPT’s potential in aiding government agencies, drawing from a case study based on a government agency in Singapore. While ChatGPT’s text generation abilities offer promise, it brings inherent challenges, including data opacity, potential misinformation, and occasional errors. These issues are especially critical in government decision-making.Public administration’s core values of transparency and accountability magnify these concerns. Ensuring AI alignment with these principles is imperative, given the potential repercussions on policy outcomes and citizen trust.AI explainability plays a central role in ChatGPT’s adoption within government agencies. To address these concerns, we propose strategies like prompt engineering, data governance, and …
Just Adjust One Prompt: Enhancing In-Context Dialogue Scoring Via Constructing The Optimal Subgraph Of Demonstrations And Prompts, Jiashu Pu, Ling Cheng, Lu Fan, Tangjie Lv, Rongsheng Zhang
Just Adjust One Prompt: Enhancing In-Context Dialogue Scoring Via Constructing The Optimal Subgraph Of Demonstrations And Prompts, Jiashu Pu, Ling Cheng, Lu Fan, Tangjie Lv, Rongsheng Zhang
Research Collection School Of Computing and Information Systems
The use of modern Large Language Models (LLMs) as chatbots still has some problems such as hallucinations and lack of empathy. Identifying these issues can help improve chatbot performance. The community has been continually iterating on reference-free dialogue evaluation methods based on large language models (LLMs) that can be readily applied. However, many of these LLM-based metrics require selecting specific datasets and developing specialized training tasks for different evaluation dimensions (e.g., coherence, informative). The developing step can be time-consuming and may need to be repeated for new evaluation dimensions. To enable efficient and flexible adaptation to diverse needs of dialogue …
Data-Driven Optimization Approaches For Dynamic Urban Logistics Operational Problems, Jingfeng Yang
Data-Driven Optimization Approaches For Dynamic Urban Logistics Operational Problems, Jingfeng Yang
Dissertations and Theses Collection (Open Access)
Given the rapid pace of urbanization, there is a pressing need to optimize urban logistics delivery operations for enhanced capacity and efficiency. Over recent decades, a multitude of optimization approaches have been put forth to address urban logistics challenges, encompassing routing and scheduling within both static and dynamic contexts. In light of the rising computational capabilities and the widespread adoption of machine learning in recent times, there is a growing body of research aimed at elucidating the seamless integration of data and machine learning within conventional urban logistics optimization models. Additionally, the ubiquitous utilization of smartphones and internet innovations presents …
The Determinants Of Creator Performance On Creative Content Platforms: Evidence From Xiaohongshu And Bilibili, Caijun Xu
Dissertations and Theses Collection (Open Access)
Content creation platforms, including Douyin, Kuaishou, Xiaohongshu, and Bilibili, have emerged as significant drivers of employment and economic growth within the digital economy. These platforms invigorate online engagement and offline consumption, serving as vital conduits that merge China’s digital and real economies. Currently, China boasts over 10 million active content creators on its leading platforms, although their earnings are markedly uneven. While some top-tier creators garner substantial profits, the majority in the mid to lower tiers grapple with profit generation and encounter challenges in enhancing their creative performance. Against this background, this study delves into the antecedents of creative performance. …
Through The Lens Of A Naturalist: How Learning About Nature Promotes Nature Connectedness Via Awe, Shu Tian Ng, Angela K. Y. Leung, Sarah Hian May Chan
Through The Lens Of A Naturalist: How Learning About Nature Promotes Nature Connectedness Via Awe, Shu Tian Ng, Angela K. Y. Leung, Sarah Hian May Chan
Research Collection School of Social Sciences
Environmental educators stress the importance of engaging with the wonders of the Earth in promoting nature connectedness. However, it remains unclear if learning about nature has an incremental effect beyond mere exposure to nature and what psychological mechanism can explain such a learning effect if it exists. To fill this gap, we propose a mediation model in which learning about nature promotes a sense of awe—a self-transcendent emotion associated with the recognition of vastness in nature. A sense of awe, in turn, promotes nature connectedness. Study 1 employed a cross-sectional survey and offered preliminary support for the proposed model, with …
The Persuasive Effect Of Ai-Synthesized Voices, Hannah H. Chang, Anirban Mukherjee
The Persuasive Effect Of Ai-Synthesized Voices, Hannah H. Chang, Anirban Mukherjee
Research Collection Lee Kong Chian School Of Business
Artificial intelligence (AI) technology seeks to emulate humans. One aspect is AI-synthesized voices, used in voice assistants (such as Amazon Alexa, Apple Siri, and Google Assistant) to assistive technologies (such as voiceover narration in product videos). For example, there are currently more than 3.25 billion voice assistants; a number that is expected to touch about 8 billion by next year (i.e., 2023) (Statista 2022). With the extensive availability and enhanced accuracy of AI-synthesized voices, consumer research is starting to examine the impact of AI-synthesized voices on consumer information processing and decision making. The extant literature, however, is relatively limited because …
Stopping The Revolving Door: Mdp-Based Decision Support For Community Corrections Placement, Xiaoquan Gao, Pengyi Shi, Nan Kong
Stopping The Revolving Door: Mdp-Based Decision Support For Community Corrections Placement, Xiaoquan Gao, Pengyi Shi, Nan Kong
Research Collection Lee Kong Chian School Of Business
Community corrections (CC) programs offer an alternative to incarceration that can reduce jail overcrowding and recidivism rates. The aim is to address the root causes behind criminal behavior, ultimately breaking the cycle of reincarceration. However, placing all eligible individuals in CC may strain case managers, resulting in reduced supervision, increased violations, and higher recidivism rates, which undermines the intended benefits for all participants in the programs. We take the first step in building a comprehensive analytical framework based on a queueing system to support the placement decisions and related decisions such as capacity planning. We develop a Markov Decision Process …
The Use Of Deception In Dementia-Care Robots: Should Robots Tell "White Lies" To Limit Emotional Distress?, Samuel R. Cox, Grace Cheong, Wei Tsang Ooi
The Use Of Deception In Dementia-Care Robots: Should Robots Tell "White Lies" To Limit Emotional Distress?, Samuel R. Cox, Grace Cheong, Wei Tsang Ooi
ROSA Journal Articles and Publications
With projections of ageing populations and increasing rates of dementia, there is need for professional caregivers. Assistive robots have been proposed as a solution to this, as they can assist people both physically and socially. However, caregivers often need to use acts of deception (such as misdirection or white lies) in order to ensure necessary care is provided while limiting negative impacts on the cared-for such as emotional distress or loss of dignity. We discuss such use of deception, and contextualise their use within robotics.
Mitigating Membership Inference Attacks Via Weighted Smoothing, Minghan Tan, Xiaofei Xie, Jun Sun, Tianhao Wang
Mitigating Membership Inference Attacks Via Weighted Smoothing, Minghan Tan, Xiaofei Xie, Jun Sun, Tianhao Wang
Research Collection School Of Computing and Information Systems
Recent advancements in deep learning have spotlighted a crucial privacy vulnerability to membership inference attack (MIA), where adversaries can determine if specific data was present in a training set, thus potentially revealing sensitive information. In this paper, we introduce a technique, weighted smoothing (WS), to mitigate MIA risks. Our approach is anchored on the observation that training samples differ in their vulnerability to MIA, primarily based on their distance to clusters of similar samples. The intuition is clusters will make model predictions more confident and increase MIA risks. Thus WS strategically introduces noise to training samples, depending on whether they …
The Psychological Science Accelerator's Covid-19 Rapid-Response Dataset, Erin M. Buchanan, Andree Hartanto
The Psychological Science Accelerator's Covid-19 Rapid-Response Dataset, Erin M. Buchanan, Andree Hartanto
Research Collection School of Social Sciences
In response to the COVID-19 pandemic, the Psychological Science Accelerator coordinated three large-scale psychological studies to examine the effects of loss-gain framing, cognitive reappraisals, and autonomy framing manipulations on behavioral intentions and affective measures. The data collected (April to October 2020) included specific measures for each experimental study, a general questionnaire examining health prevention behaviors and COVID-19 experience, geographical and cultural context characterization, and demographic information for each participant. Each participant started the study with the same general questions and then was randomized to complete either one longer experiment or two shorter experiments. Data were provided by 73,223 participants with …
A Black-Box Attack On Code Models Via Representation Nearest Neighbor Search, Jie Zhang, Wei Ma, Qiang Hu, Shangqing Liu, Xiaofei Xie, Yves Le Traon, Yang Liu
A Black-Box Attack On Code Models Via Representation Nearest Neighbor Search, Jie Zhang, Wei Ma, Qiang Hu, Shangqing Liu, Xiaofei Xie, Yves Le Traon, Yang Liu
Research Collection School Of Computing and Information Systems
Existing methods for generating adversarial code examples face several challenges: limted availability of substitute variables, high verification costs for these substitutes, and the creation of adversarial samples with noticeable perturbations. To address these concerns, our proposed approach, RNNS, uses a search seed based on historical attacks to find potential adversarial substitutes. Rather than directly using the discrete substitutes, they are mapped to a continuous vector space using a pre-trained variable name encoder. Based on the vector representation, RNNS predicts and selects better substitutes for attacks. We evaluated the performance of RNNS across six coding tasks encompassing three programming languages: Java, …
Weakly-Supervised Semantic Segmentation, Zhaozheng Chen
Weakly-Supervised Semantic Segmentation, Zhaozheng Chen
Dissertations and Theses Collection (Open Access)
Semantic segmentation is a fundamental task in computer vision that assigns a label to every pixel in an image based on the semantic meaning of the objects present. It demands a large amount of pixel-level labeled images for training deep models. Weakly-supervised semantic segmentation (WSSS) is a more feasible approach that uses only weak annotations to learn the segmentation task. Image-level label based WSSS is the most challenging and popular, where only the class label for the entire image is provided as supervision. To address this challenge, Class Activation Map (CAM) has emerged as a powerful technique in WSSS. CAM …
Supporting Software Engineers With Large Language Model-Based Automation, Ting Zhang
Supporting Software Engineers With Large Language Model-Based Automation, Ting Zhang
Dissertations and Theses Collection (Open Access)
In recent years, software engineering (SE) has witnessed significant growth, leading to the creation and sharing of an abundance of software artifacts such as source code, bug reports, and pull requests. Analyzing these artifacts is crucial for comprehending the sentiments of software developers and automating various SE tasks, ultimately leading to more human-centered automated SE and enhancing software development efficiency. However, the diverse and unstructured nature of software text poses a significant challenge to this analysis. In response, researchers have investigated a variety of approaches, including the utilization of natural language processing techniques. The advent of large language models (LLMs), …
Towards Securing Smart Contracts Systematically, Duy Tai Nguyen
Towards Securing Smart Contracts Systematically, Duy Tai Nguyen
Dissertations and Theses Collection (Open Access)
Smart contracts are a groundbreaking technique that allows users to programmatically modify the state of the blockchain. They are essentially self-enforcing programs that are deployed and executed on top of the blockchain. In recent years, we have witnessed various smart contract incidents that led to substantial financial losses and even business closures. These incidents mainly arise from design flaws in Solidity, a dominant programming language for writing smart contracts, which complicates the process of detecting and repairing vulnerabilities. Furthermore, there is a growing interest in attacking smart contracts by the attackers. This thesis is dedicated to developing effective methods to …
Technical Maturity And Network Effects Of Xf Artificial Intelligence Open Platform, Tao Jiang
Technical Maturity And Network Effects Of Xf Artificial Intelligence Open Platform, Tao Jiang
Dissertations and Theses Collection (Open Access)
Studying the impact mechanism of the commercial value of artificial intelligence open technology platforms has theoretical and practical significance. This article aims to enrich and expand the theoretical research on technology maturity, value co creation, and network effects on open technology platforms at home and abroad through empirical research on artificial intelligence open technology platforms and ecology. This study takes XF's open technology platform case as the research object, and based on technology maturity theory, value co creation, and network effects theory, examines the network effect value creation mechanism of open technology platforms driven by technology maturity in three development …
Deep Isolation Forest For Anomaly Detection, Hongzuo Xu, Guansong Pang, Yijie Wang, Yongjun Wang
Deep Isolation Forest For Anomaly Detection, Hongzuo Xu, Guansong Pang, Yijie Wang, Yongjun Wang
Research Collection School Of Computing and Information Systems
Isolation forest (iForest) has been emerging as arguably the most popular anomaly detector in recent years due to its general effectiveness across different benchmarks and strong scalability. Nevertheless, its linear axis-parallel isolation method often leads to (i) failure in detecting hard anomalies that are difficult to isolate in high-dimensional/non-linear-separable data space, and (ii) notorious algorithmic bias that assigns unexpectedly lower anomaly scores to artefact regions. These issues contribute to high false negative errors. Several iForest extensions are introduced, but they essentially still employ shallow, linear data partition, restricting their power in isolating true anomalies. Therefore, this paper proposes deep isolation …
Neural Airport Ground Handling, Yaoxin Wu, Jianan Zhou, Yunwen Xia, Xianli Zhang, Zhiguang Cao, Jie Zhang
Neural Airport Ground Handling, Yaoxin Wu, Jianan Zhou, Yunwen Xia, Xianli Zhang, Zhiguang Cao, Jie Zhang
Research Collection School Of Computing and Information Systems
Airport ground handling (AGH) offers necessary operations to flights during their turnarounds and is of great importance to the efficiency of airport management and the economics of aviation. Such a problem involves the interplay among the operations that leads to NP-hard problems with complex constraints. Hence, existing methods for AGH are usually designed with massive domain knowledge but still fail to yield high-quality solutions efficiently. In this paper, we aim to enhance the solution quality and computation efficiency for solving AGH. Particularly, we first model AGH as a multiple-fleet vehicle routing problem (VRP) with miscellaneous constraints including precedence, time windows, …
C³: Code Clone-Based Identification Of Duplicated Components, Yanming Yang, Ying Zou, Xing Hu, David Lo, Chao Ni, John C. Grundy, Xin: Xia
C³: Code Clone-Based Identification Of Duplicated Components, Yanming Yang, Ying Zou, Xing Hu, David Lo, Chao Ni, John C. Grundy, Xin: Xia
Research Collection School Of Computing and Information Systems
Reinventing the wheel is a detrimental programming practice in software development that frequently results in the introduction of duplicated components. This practice not only leads to increased maintenance and labor costs but also poses a higher risk of propagating bugs throughout the system. Despite numerous issues introduced by duplicated components in software, the identification of component-level clones remains a significant challenge that existing studies struggle to effectively tackle. Specifically, existing methods face two primary limitations that are challenging to overcome: 1) Measuring the similarity between different components presents a challenge due to the significant size differences among them; 2) Identifying …
Combat Covid-19 At National Level Using Risk Stratification With Appropriate Intervention, Xuan Jin, Kar Way Tan
Combat Covid-19 At National Level Using Risk Stratification With Appropriate Intervention, Xuan Jin, Kar Way Tan
Research Collection School Of Computing and Information Systems
In the national battle against COVID-19, harnessing population-level big data is imperative, enabling authorities to devise effective care policies, allocate healthcare resources efficiently, and enact targeted interventions. Singapore adopted the Home Recovery Programme (HRP) in September 2021, diverting low-risk COVID-19 patients to home care to ease hospital burdens amid high vaccination rates and mild symptoms. While a patient's suitability for HRP could be assessed using broad-based criteria, integrating machine learning (ML) model becomes invaluable for identifying high-risk patients prone to severe illness, facilitating early medical assessment. Most prior studies have traditionally depended on clinical and laboratory data, necessitating initial clinic …
Vision Paper: Advancing Of Ai Explainability For The Use Of Chatgpt In Government Agencies: Proposal Of A 4-Step Framework, Hui Shan Lee, Shankararaman, Venky, Eng Lieh Ouh
Vision Paper: Advancing Of Ai Explainability For The Use Of Chatgpt In Government Agencies: Proposal Of A 4-Step Framework, Hui Shan Lee, Shankararaman, Venky, Eng Lieh Ouh
Research Collection School Of Computing and Information Systems
This paper explores ChatGPT’s potential in aiding government agencies, drawing from a case study based on a government agency in Singapore. While ChatGPT’s text generation abilities offer promise, it brings inherent challenges, including data opacity, potential misinformation, and occasional errors. These issues are especially critical in government decision-making.Public administration’s core values of transparency and accountability magnify these concerns. Ensuring AI alignment with these principles is imperative, given the potential repercussions on policy outcomes and citizen trust.AI explainability plays a central role in ChatGPT’s adoption within government agencies. To address these concerns, we propose strategies like prompt engineering, data governance, and …
Do Contributing Files Provide Information About Oss Newcomers' Onboarding Barriers?, Felipe Fronchetti, David Shepherd, Igor Wiese, Christoph Treude, Marco Gerosa, Igor Steinmacher
Do Contributing Files Provide Information About Oss Newcomers' Onboarding Barriers?, Felipe Fronchetti, David Shepherd, Igor Wiese, Christoph Treude, Marco Gerosa, Igor Steinmacher
Research Collection School Of Computing and Information Systems
Effectively onboarding newcomers is essential for the success of open source projects. These projects often provide onboarding guidelines in their ‘CONTRIBUTING’ files (e.g., CONTRIBUTING.md on GitHub). These files explain, for example, how to find open tasks, implement solutions, and submit code for review. However, these files often do not follow a standard structure, can be too large, and miss barriers commonly found by newcomers. In this paper, we propose an automated approach to parse these CONTRIBUTING files and assess how they address onboarding barriers. We manually classified a sample of files according to a model of onboarding barriers from the …
Deeparc: Modularizing Neural Networks For The Model Maintenance, Xiaoning Ren, Yun Lin, Yinxing Xue, Ruofan Liu, Jun Sun, Zhiyong Feng, Jinsong Dong
Deeparc: Modularizing Neural Networks For The Model Maintenance, Xiaoning Ren, Yun Lin, Yinxing Xue, Ruofan Liu, Jun Sun, Zhiyong Feng, Jinsong Dong
Research Collection School Of Computing and Information Systems
Neural networks are an emerging data-driven programming paradigm widely used in many areas. Unlike traditional software systems consisting of decomposable modules, a neural network is usually delivered as a monolithic package, raising challenges for some maintenance tasks such as model restructure and re-adaption. In this work, we propose DeepArc, a novel modularization method for neural networks, to reduce the cost of model maintenance tasks. Specifically, DeepArc decomposes a neural network into several consecutive modules, each of which encapsulates consecutive layers with similar semantics. The network modularization facilitates practical tasks such as refactoring the model to preserve existing features (e.g., model …
Exposure To Climate Change Information Predicts Public Support For Solar Geoengineering In Singapore And The United States, Sonny Rosenthal, Peter J. Irvine, Christopher L. Cummings, Shirley S. Ho
Exposure To Climate Change Information Predicts Public Support For Solar Geoengineering In Singapore And The United States, Sonny Rosenthal, Peter J. Irvine, Christopher L. Cummings, Shirley S. Ho
Research Collection College of Integrative Studies
Solar geoengineering is a controversial climate policy measure that could lower global temperature by increasing the amount of light reflected by the Earth. As scientists and policymakers increasingly consider this idea, an understanding of the level and drivers of public support for its research and potential deployment will be key. This study focuses on the role of climate change information in public support for research and deployment of stratospheric aerosol injection (SAI) in Singapore (n = 503) and the United States (n = 505). Findings were consistent with the idea that exposure to information underlies support for research and deployment. …
Forecasting Traffic Speed During Daytime From Google Street View Images Using Deep Learning, Junfeng Jiao, Huihai Wang
Forecasting Traffic Speed During Daytime From Google Street View Images Using Deep Learning, Junfeng Jiao, Huihai Wang
Research Collection College of Integrative Studies
Traffic forecasting plays an important role in urban planning. Deep learning methods outperform traditional traffic flow forecasting models because of their ability to capture spatiotemporal characteristics of traffic conditions. However, these methods require high-quality historical traffic data, which can be both difficult to acquire and non-comprehensive, making it hard to predict traffic flows at the city scale. To resolve this problem, we implemented a deep learning method, SceneGCN, to forecast traffic speed at the city scale. The model involves two steps: firstly, scene features are extracted from Google Street View (GSV) images for each road segment using pretrained Resnet18 models. …
Software Composition Analysis For Vulnerability Detection: An Empirical Study On Java Projects, Lida Zhao, Sen Chen, Zhengzi Xu, Lyuye Zhang, Jiahui Wu, Jun Sun, Yang Liu
Software Composition Analysis For Vulnerability Detection: An Empirical Study On Java Projects, Lida Zhao, Sen Chen, Zhengzi Xu, Lyuye Zhang, Jiahui Wu, Jun Sun, Yang Liu
Research Collection School Of Computing and Information Systems
Software composition analysis (SCA) tools are proposed to detect potential vulnerabilities introduced by open-source software (OSS) imported as third-party libraries (TPL). With the increasing complexity of software functionality, SCA tools may encounter various scenarios during the dependency resolution process, such as diverse formats of artifacts, diverse dependency imports, and diverse dependency specifications. However, there still lacks a comprehensive evaluation of SCA tools for Java that takes into account the above scenarios. This could lead to a confined interpretation of comparisons, improper use of tools, and hinder further improvements of the tools. To fill this gap, we proposed an Evaluation Model …
The Value Of Official Website Information In The Credit Risk Evaluation Of Smes, Cuiqing Jiang, Chang Yin, Qian Tang, Zhao Wang
The Value Of Official Website Information In The Credit Risk Evaluation Of Smes, Cuiqing Jiang, Chang Yin, Qian Tang, Zhao Wang
Research Collection School Of Computing and Information Systems
The official websites of small and medium-sized enterprises (SMEs) not only reflect the willingness of an enterprise to disclose information voluntarily, but also can provide information related to the enterprises’ historical operations and performance. This research investigates the value of official website information in the credit risk evaluation of SMEs. To study the effect of different kinds of website information on credit risk evaluation, we propose a framework to mine effective features from two kinds of information disclosed on the official website of a SME—design-based information and content-based information—in predicting its credit risk. We select the SMEs in the software …
Llm-Adapters: An Adapter Family For Parameter-Efficient Fine-Tuning Of Large Language Models, Zhiqiang Hu, Lei Wang, Yihuai Lan, Wanyu Xu, Ee-Peng Lim, Lidong Bing, Xing Xu, Soujanya Poria, Roy Ka-Wei Lee
Llm-Adapters: An Adapter Family For Parameter-Efficient Fine-Tuning Of Large Language Models, Zhiqiang Hu, Lei Wang, Yihuai Lan, Wanyu Xu, Ee-Peng Lim, Lidong Bing, Xing Xu, Soujanya Poria, Roy Ka-Wei Lee
Research Collection School Of Computing and Information Systems
The success of large language models (LLMs), like GPT-4 and ChatGPT, has led to the development of numerous cost-effective and accessible alternatives that are created by finetuning open-access LLMs with task-specific data (e.g., ChatDoctor) or instruction data (e.g., Alpaca). Among the various fine-tuning methods, adapter-based parameter-efficient fine-tuning (PEFT) is undoubtedly one of the most attractive topics, as it only requires fine-tuning a few external parameters instead of the entire LLMs while achieving comparable or even better performance. To enable further research on PEFT methods of LLMs, this paper presents LLMAdapters, an easy-to-use framework that integrates various adapters into LLMs and …
Graph Contrastive Learning With Stable And Scalable Spectral Encoding, Deyu Bo, Yuan Fang, Yang Liu, Chuan Shi
Graph Contrastive Learning With Stable And Scalable Spectral Encoding, Deyu Bo, Yuan Fang, Yang Liu, Chuan Shi
Research Collection School Of Computing and Information Systems
Graph contrastive learning (GCL) aims to learn representations by capturing the agreements between different graph views. Traditional GCL methods generate views in the spatial domain, but it has been recently discovered that the spectral domain also plays a vital role in complementing spatial views. However, existing spectral-based graph views either ignore the eigenvectors that encode valuable positional information, or suffer from high complexity when trying to address the instability of spectral features. To tackle these challenges, we first design an informative, stable, and scalable spectral encoder, termed EigenMLP, to learn effective representations from the spectral features. Theoretically, EigenMLP is invariant …
Rome: Evaluating Pre-Trained Vision-Language Models On Reasoning Beyond Visual Common Sense, Kankan Zhou, Eason Lai, Au Wei Bin Yeong, Kyriakos Mouratidis, Jing Jiang
Rome: Evaluating Pre-Trained Vision-Language Models On Reasoning Beyond Visual Common Sense, Kankan Zhou, Eason Lai, Au Wei Bin Yeong, Kyriakos Mouratidis, Jing Jiang
Research Collection School Of Computing and Information Systems
Humans possess a strong capability for reasoning beyond common sense. For example, given an unconventional image of a goldfish laying on the table next to an empty fishbowl, a human would effortlessly determine that the fish is not inside the fishbowl. The case, however, may be different for a vision-language model, whose reasoning could gravitate towards the common scenario that the fish is inside the bowl, despite the visual input. In this paper, we introduce a novel probing dataset named ROME (reasoning beyond commonsense knowledge) to evaluate whether the state-of-the-art pre-trained vision-language models have the reasoning capability to correctly interpret …
Examining The Inter-Consistency Of Large Language Models: An In-Depth Analysis Via Debate, Kai Xiong, Xiao Ding, Yixin Cao, Ting Liu, Bing Qin
Examining The Inter-Consistency Of Large Language Models: An In-Depth Analysis Via Debate, Kai Xiong, Xiao Ding, Yixin Cao, Ting Liu, Bing Qin
Research Collection School Of Computing and Information Systems
Large Language Models (LLMs) have shown impressive capabilities in various applications, but they still face various inconsistency issues. Existing works primarily focus on the inconsistency issues within a single LLM, while we complementarily explore the inter-consistency among multiple LLMs for collaboration. To examine whether LLMs can collaborate effectively to achieve a consensus for a shared goal, we focus on commonsense reasoning, and introduce a formal debate framework (FORD) to conduct a three-stage debate among LLMs with real-world scenarios alignment: fair debate, mismatched debate, and roundtable debate. Through extensive experiments on various datasets, LLMs can effectively collaborate to reach a consensus …