Digital Commons Network^™

Hypergraphs With Attention On Reviews For Explainable Recommendation, Theis E. Jendal, Trung Hoang Le, Hady Wirawan Lauw, Matteo Lissandrini, Peter Dolog, Katja Hose

Research Collection School Of Computing and Information Systems

Given a recommender system based on reviews, the challenges are how to effectively represent the review data and how to explain the produced recommendations. We propose a novel review-specific Hypergraph (HG) model, and further introduce a model-agnostic explainability module. The HG model captures high-order connections between users, items, aspects, and opinions while maintaining information about the review. The explainability module can use the HG model to explain a prediction generated by any model. We propose a path-restricted review-selection method biased by the user preference for item reviews and propose a novel explanation method based on a review graph. Experiments on …

Revisiting The Markov Property For Machine Translation, Cunxiao Du, Hao Zhou, Zhaopeng Tu, Jing Jiang

Research Collection School Of Computing and Information Systems

In this paper, we re-examine the Markov property in the context of neural machine translation. We design a Markov Autoregressive Transformer (MAT) and undertake a comprehensive assessment of its performance across four WMT benchmarks. Our findings indicate that MAT with an order larger than 4 can generate translations with quality on par with that of conventional autoregressive transformers. In addition, counter-intuitively, we also find that the advantages of utilizing a higher-order MAT do not specifically contribute to the translation of longer sentences.

Generative Ai In Finance: Risks And Potential Solutions, Nydia Remolina Leon

Research Collection Yong Pung How School Of Law

Generative Artificial Intelligence captured the attention of academics, policymakers, the private sector, and some regulators in 2022 after the launch of ChatGPT and its widespread adoption worldwide. Then, during the World Economic Forum session in 2023, Microsoft Chairman and Chief Executive Officer Satya Nadella said that the ‘golden age’ of AI is underway and generative AI is set to play a big role in it. Accordingly, Microsoft has invested billions of dollars into OpenAI, the company behind the launch of ChatGPT. Additionally, Google and Meta have also created their own generative AI models. Given the multiplicity of potential use cases …

Understanding The Impact Of Trade Policy Effect Uncertainty On Firm-Level Innovation Investment: A Deep Learning Approach, Daniel Chang, Nan Hu, Peng Liang, Morgan Swink

Research Collection School Of Computing and Information Systems

Integrating the real options perspective and resource dependence theory, this study examines how firms adjust their innovation investments to trade policy effect uncertainty (TPEU), a less studied type of firm specific, perceived environmental uncertainty in which managers have difficulty predicting how potential policy changes will affect business operations. To develop a text-based, context-dependent, time-varying measure of firm-level perceived TPEU, we apply Bidirectional Encoder Representations from Transformers (BERT), a state-of-the-art deep learning approach. We apply BERT to analyze the texts of mandatory Management Discussion and Analysis (MD&A) sections of annual reports for a sample of 22,669 firm-year observations from 3,181 unique …

Analyzing Global Utilization And Missed Opportunities In Debt-For-Nature Swaps With Generative Ai, Nataliya Tkachenko, Simon Frieder, Ryan-Rhys Griffiths, Christoph Nedopil

Sim Kee Boon Institute for Financial Economics

We deploy a prompt-augmented GPT-4 model to distill comprehensive datasets on the global application of debt-for-nature swaps (DNS), a pivotal financial tool for environmental conservation. Our analysis includes 195 nations and identifies 21 countries that have not yet used DNS before as prime candidates for DNS. A significant proportion demonstrates consistent commitments to conservation finance (0.86 accuracy as compared to historical swaps records). Conversely, 35 countries previously active in DNS before 2010 have since been identified as unsuitable. Notably, Argentina, grappling with soaring inflation and a substantial sovereign debt crisis, and Poland, which has achieved economic stability and gained access …

M3sa: Multimodal Sentiment Analysis Based On Multi-Scale Feature Extraction And Multi-Task Learning, Changkai Lin, Hongju Cheng, Qiang Rao, Yang Yang

Research Collection School Of Computing and Information Systems

Sentiment analysis plays an indispensable part in human-computer interaction. Multimodal sentiment analysis can overcome the shortcomings of unimodal sentiment analysis by fusing multimodal data. However, how to extracte improved feature representations and how to execute effective modality fusion are two crucial problems in multimodal sentiment analysis. Traditional work uses simple sub-models for feature extraction, and they ignore features of different scales and fuse different modalities of data equally, making it easier to incorporate extraneous information and affect analysis accuracy. In this paper, we propose a Multimodal Sentiment Analysis model based on Multi-scale feature extraction and Multi-task learning (M 3 SA). …

Delving Into Multimodal Prompting For Fine-Grained Visual Classification, Xin Jiang, Hao Tang, Junyao Gao, Xiaoyu Du, Shengfeng He, Zechao Li

Research Collection School Of Computing and Information Systems

Fine-grained visual classification (FGVC) involves categorizing fine subdivisions within a broader category, which poses challenges due to subtle inter-class discrepancies and large intra-class variations. However, prevailing approaches primarily focus on uni-modal visual concepts. Recent advancements in pre-trained vision-language models have demonstrated remarkable performance in various high-level vision tasks, yet the applicability of such models to FGVC tasks remains uncertain. In this paper, we aim to fully exploit the capabilities of cross-modal description to tackle FGVC tasks and propose a novel multimodal prompting solution, denoted as MP-FGVC, based on the contrastive language-image pertaining (CLIP) model. Our MP-FGVC comprises a multimodal prompts …

Public Offices In Processes Of Constitutional Development, J.G. Allen

Research Collection Yong Pung How School Of Law

What factors drive constitutional change and sustain positive transformation? How are democratic values recognised, restored, and preserved through constitutional change? How can these questions be answered in a manner that is relevant to most of the world? This collection brings together leading and emerging scholars and practitioners to explore the relationship between democratic consolidation and constitutional endurance through consideration of recent experiences in seven African and Asian states that have undergone an understudied democratising event in the past decade: Ethiopia, The Gambia, Malaysia, Maldives, Myanmar, Sri Lanka, and Thailand. Building on the empirical surveys, seven thematic chapters offer analytical insights …

Mitigating Fine-Grained Hallucination By Fine-Tuning Large Vision-Language Models With Caption Rewrites, Lei Wang, Jiabang He, Shenshen Li, Ning Liu, Ee-Peng Lim

Research Collection School Of Computing and Information Systems

Large language models (LLMs) have shown remarkable performance in natural language processing (NLP) tasks. To comprehend and execute diverse human instructions over image data, instruction-tuned large vision-language models (LVLMs) have been introduced. However, LVLMs may suffer from different types of object hallucinations. Nevertheless, LVLMs are evaluated for coarse-grained object hallucinations only (i.e., generated objects non-existent in the input image). The fine-grained object attributes and behaviors non-existent in the image may still be generated but not measured by the current evaluation methods. In this paper, we thus focus on reducing fine-grained hallucinations of LVLMs. We propose ReCaption, a framework that consists …

Simple Image-Level Classification Improves Open-Vocabulary Object Detection, Ruohuan Fang, Guansong Pang, Xiao Bai

Research Collection School Of Computing and Information Systems

Open-Vocabulary Object Detection (OVOD) aims to detect novel objects beyond a given set of base categories on which the detection model is trained. Recent OVOD methods focus on adapting the image-level pre-trained vision-language models (VLMs), such as CLIP, to a region-level object detection task via, eg., region-level knowledge distillation, regional prompt learning, or region-text pre-training, to expand the detection vocabulary. These methods have demonstrated remarkable performance in recognizing regional visual concepts, but they are weak in exploiting the VLMs' powerful global scene understanding ability learned from the billion-scale image-level text descriptions. This limits their capability in detecting hard objects of …

Reverse Multi-Choice Dialogue Commonsense Inference With Graph-Of-Thought, Li Zheng, Hao Fei, Fei Li, Bobo Li, Lizi Liao, Donghong Ji, Chong Teng

Research Collection School Of Computing and Information Systems

With the proliferation of dialogic data across the Internet, the Dialogue Commonsense Multi-choice Question Answering (DC-MCQ) task has emerged as a response to the challenge of comprehending user queries and intentions. Although prevailing methodologies exhibit effectiveness in addressing single-choice questions, they encounter difficulties in handling multi-choice queries due to the heightened intricacy and informational density. In this paper, inspired by the human cognitive process of progressively excluding options, we propose a three-step Reverse Exclusion Graph-of-Thought (ReX-GoT) framework, including Option Exclusion, Error Analysis, and Combine Information. Specifically, our ReX-GoT mimics human reasoning by gradually excluding irrelevant options and learning the reasons …

Strategic Diplomacy: The Singapore Case, Country Report For The Project On ‘Strategic Diplomacy For 21st Century Defence And Statecraft’, Evelyn Goh, Wee-Kiat Lim

CCX Research

How does Singapore conduct strategic diplomacy despite being a small and constrained state? This report first identifies the major long-term drivers affecting Singapore’s security, both at the domestic level (rapidly ageing population, immigrant assimilation, and growing societal fault-lines) and at the international or systemic level (changing global order, power of technology, slow collective action on climate change). Then it analyses how Singapore strategists deal with two of their most prominent problem-sets: (i) positioning Singapore in relation to the US-China rivalry and the changing international order; and (ii) tackling climate change as a collective action problem. Both problem-sets illustrate how Singapore …

Deploying Chatbots To Build Students' Critical Thinking Skills: Leveraging Generative Ai Effectively And Purposefully In Higher Education, Sun Sun Lim, Tamas Makany

Research Collection College of Integrative Studies

No abstract provided.

Language-Related Misunderstanding At Work: What It Is, Why It Occurs And What Organizations Can Do About It, John Fiset, Devasheesh P. Bhave

Research Collection Lee Kong Chian School Of Business

Language is the foundation of human interaction. It plays a central role in facilitating effective communication by allowing people to express their thoughts, share essential information and establish connections with one another.

The Effects Of Language-Related Misunderstanding At Work, John Fiset, Devasheesh P. Bhave, Nilotpal Jha

Research Collection Lee Kong Chian School Of Business

Demographic, technological, and global trends have brought the language used at the workplace to the forefront. A growing body of research reveals that language could result in misunderstanding at work, and influence employees' performance and attitudinal outcomes. Language at work encompasses standard language (e.g., English) as well as several hybrid forms of language (non-native accents, code-switching, and jargon). We delineate how these forms of language could result in misunderstanding. We then identify relational, affective, and informational mechanisms that underlie the relationship between language-related misunderstanding and employees' performance and attitudinal outcomes, and highlight key boundary conditions. In doing so, we uncover …

The Impact Of The Business School Research, Kai Peters, Howard Thomas

Research Collection Lee Kong Chian School Of Business

Producing high-quality research has long been an important strategic objective for business schools. Faculty research has typically been evaluated by articles appearing in highly regarded academic journals and by citation counts. Increasingly, however, government funding bodies are seeking more than just appearances in 4* journals, they are looking for meaningful societal impact. To this end researchers, in various countries, must submit case studies to funding bodies outlining concrete examples of impact in addition to the original research articles. In the future, the financial reward for high-impact case studies will significantly supersede the reward for journal prestige and citation counts.

Conceptthread: Visualizing Threaded Concepts In Mooc Videos, Zhiguang Zhou, Li Ye, Lihong Cai, Lei Wang, Yigang Wang, Yongheng Wang, Wei Chen, Yong Wang

Research Collection School Of Computing and Information Systems

Massive Open Online Courses (MOOCs) platforms are becoming increasingly popular in recent years. Online learners need to watch the whole course video on MOOC platforms to learn the underlying new knowledge, which is often tedious and time-consuming due to the lack of a quick overview of the covered knowledge and their structures. In this paper, we propose ConceptThread , a visual analytics approach to effectively show the concepts and the relations among them to facilitate effective online learning. Specifically, given that the majority of MOOC videos contain slides, we first leverage video processing and speech analysis techniques, including shot recognition, …

A Unified Framework For Contextual And Factoid Question Generation, Chenhe Dong, Ying Shen, Shiyang Lin, Zhenzhou Lin, Yang Deng

Research Collection School Of Computing and Information Systems

Question generation (QG) aims to automatically generate fluent and relevant questions, where the two most mainstream directions are generating questions from unstructured contextual texts (CQG), such as news articles, and generating questions from structured factoid texts (FQG), such as knowledge graphs or tables. Existing methods for these two tasks mainly face challenges of limited internal structural information as well as scarce background information, while these two tasks can benefit each other for alleviating these issues. For example, when meeting the entity mention “United Kingdom” in CQG, it can be inferred that it is a country in European continent based on …

Internal And Social Sources Shape Judgments About The Mental And Physical Nature Of An Experience, Jacinth Jia Xin Tan, Alexander Karan, Dolores Albarracin

Research Collection School of Social Sciences

Although humans are intuitive dualists, little is known about whether they hold lay beliefs about the origins or sources of their intuitive perceptions of what is physical and what is mental. Drawing on theories of the sources of phenomenological experiences, we examined if people hold beliefs about the internal and social origins of judments that their experiences are physical or mental. In Study 1, participants provided physical or mental judgments about a range of personal experiences, and reported relying on both internal (i.e., examining own body and thoughts) and social (i.e., observing others) sources as information for their judgments. To …

Rethinking The Inclusionary Potential Of Religious Institutions: The Case Of Gurdwaras In Singapore, Siew Ying Shee, Orlando Woods

Research Collection College of Integrative Studies

Whilst Singapore’s Sikh community is relatively small, it is also heterogeneous. Its diversity reflects differences in ancestral and socio-economic backgrounds. As spaces of worship that regularly bring together the Sikh community in space and time, Sikh temples—gurdwaras––are often conceived as important places through which a shared sense of religiously-defined community is reproduced. Yet, as much as religion can provide a bridge that integrates people of different ethnic, racial, national, and linguistic groups into a single faith community, so too can it act as a buttress through which differences and divisions are enforced within the community. We argue that whilst gurdwaras …

Climate-Related Shareholder Activism As Corporate Democracy: A Call To Reform “Acting In Concert” Rules, Dan W. Puchniak, Umakanth Varottil

Research Collection Yong Pung How School Of Law

Climate change is an issue of global importance, which may turn out to be the issue of this century. Companies are at the core of both the problems and solutions for climate change. Given this reality, it is astounding that in virtually all jurisdictions in the world ‘acting in concert rules,’ which were designed decades ago to facilitate an efficient market for corporate control, effectively prevent shareholders who hold a majority of shares from democratically replacing boards of dirty companies. Our Article exposes this overlooked reality by undertaking the first in-depth comparative analysis of acting in concert rules with a …

Estimating Propensity For Causality-Based Recommendation Without Exposure Data, Zhongzhou Liu, Yuan Fang, Min Wu

Research Collection School Of Computing and Information Systems

Causality-based recommendation systems focus on the causal effects of user-item interactions resulting from item exposure (i.e., which items are recommended or exposed to the user), as opposed to conventional correlation-based recommendation. They are gaining popularity due to their multi-sided benefits to users, sellers and platforms alike. However, existing causality-based recommendation methods require additional input in the form of exposure data and/or propensity scores (i.e., the probability of exposure) for training. Such data, crucial for modeling causality in recommendation, are often not available in real-world situations due to technical or privacy constraints. In this paper, we bridge the gap by proposing …

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 …

Large Language Models As Source Planner For Personalized Knowledge-Grounded Dialogues, Hongru Wang, Minda Hu, Yang Deng, Rui Wang, Fei Mi, Weichao Wang, Yasheng Wang, Wai-Chung Kwan, Irwin King, Kam-Fai Wong

Research Collection School Of Computing and Information Systems

Open-domain dialogue system usually requires different sources of knowledge to generate more informative and evidential responses. However, existing knowledge-grounded dialogue systems either focus on a single knowledge source or overlook the dependency between multiple sources of knowledge, which may result in generating inconsistent or even paradoxical responses. To incorporate multiple knowledge sources and dependencies between them, we propose SAFARI, a novel framework that leverages the exceptional capabilities of large language models (LLMs) in planning, understanding, and incorporating under both supervised and unsupervised settings. Specifically, SAFARI decouples the knowledge grounding into multiple sources and response generation, which allows easy extension to …

Buffering The Negative Impacts Of Age Diversity On Company Performance And Innovation: The Roles Of Knowledge Transfer And Environmental Uncertainty, Tiecheng Xu

Dissertations and Theses Collection (Open Access)

The VUCA (Volatility, Uncertainty, Complexity, Ambiguity) era has resulted in significant uncertainty in the global economy, while deglobalization in international politics and economics, and the interweaving of old and new contradictions, have presented substantial challenges to businesses. On the other hand, aging is a crucial issue that China and the world at large are currently facing. It is essential to study the relationship between employee age structure and enterprise performance.

Different researchers have provided empirical analyses of the effects of age diversity on organizational performance and innovation, but the conclusions are not consistent. According to the research in this paper, …

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 …

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 …

Robust Prompt Optimization For Large Language Models Against Distribution Shifts, Moxin Li, Wenjie Wang, Fuli Feng, Yixin Cao, Jizhi Zhang, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Large Language Model (LLM) has demonstrated significant ability in various Natural Language Processing tasks. However, their effectiveness is highly dependent on the phrasing of the task prompt, leading to research on automatic prompt optimization using labeled task data. We reveal that these prompt optimization techniques are vulnerable to distribution shifts such as subpopulation shifts, which are common for LLMs in real-world scenarios such as customer reviews analysis. In this light, we propose a new problem of robust prompt optimization for LLMs against distribution shifts, which requires the prompt optimized over the labeled source group can simultaneously generalize to an unlabeled …

Molca: Molecular Graph-Language Modeling With Cross-Modal Projector And Uni-Modal Adapter, Zhiyuan Liu, Sihang Li, Yanchen Luo, Hao Fei, Yixin Cao, Kenji Kawaguchi, Xiang Wang, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Language Models (LMs) have demonstrated impressive molecule understanding ability on various 1D text-related tasks. However, they inherently lack 2D graph perception — a critical ability of human professionals in comprehending molecules’ topological structures. To bridge this gap, we propose MolCA: Molecular Graph-Language Modeling with Cross-Modal Projector and Uni-Modal Adapter. MolCA enables an LM (i.e., Galactica) to understand both text- and graph-based molecular contents via the cross-modal projector. Specifically, the cross-modal projector is implemented as a QFormer to connect a graph encoder’s representation space and an LM’s text space. Further, MolCA employs a uni-modal adapter (i.e., LoRA) for the LM’s efficient …

Wsdms: Debunk Fake News Via Weakly Supervised Detection Of Misinforming Sentences With Contextualized Social Wisdom, Ruichao Yang, Wei Gao, Jing Ma, Hongzhan Lin, Zhiwei Yang

Research Collection School Of Computing and Information Systems

In recent years, we witness the explosion of false and unconfirmed information (i.e., rumors) that went viral on social media and shocked the public. Rumors can trigger versatile, mostly controversial stance expressions among social media users. Rumor verification and stance detection are different yet relevant tasks. Fake news debunking primarily focuses on determining the truthfulness of news articles, which oversimplifies the issue as fake news often combines elements of both truth and falsehood. Thus, it becomes crucial to identify specific instances of misinformation within the articles. In this research, we investigate a novel task in the field of fake news …