Digital Commons Network^™

Learning To Generate Explainable Stock Predictions Using Self‑Reflective Large Language Models, Kelvin J.L. Koa, Yunshan Ma, Ritchie Ng, Tat‑Seng Chua

Research Collection School Of Computing and Information Systems

Explaining stock predictions is generally a difficult task for traditional non-generative deep learning models, where explanations are limited to visualizing the attention weights on important texts. Today, Large Language Models (LLMs) present a solution to this problem, given their known capabilities to generate human-readable explanations for their decision-making process. However, the task of stock prediction remains challenging for LLMs, as it requires the ability to weigh the varying impacts of chaotic social texts on stock prices. The problem gets progressively harder with the introduction of the explanation component, which requires LLMs to explain verbally why certain factors are more important …

Untangling Influence: The Effect Of Follower-Followee Comparison On Social Media Engagement, Yi Peng, Liling Lu

Research Collection Lee Kong Chian School Of Business

Social media platforms and marketers are keen on identifying truly influential creators. Number of followers (i.e., those who follow creators) and number of followees (i.e., those who are followed by creators) serve as cues to infer creators' influence. However, a cue of creators' actual influence is under-addressed and its effect on social media engagement remains to be explored. This research fills the gap in the literature by investigating how the cue of creators' actual influence (i.e., follower-followee comparison) may affect followers' engagement behavior. The study further examines the moderation effects of media-, topic-, and creator-related factors. The present work leverages …

Plug-And-Play Policy Planner For Large Language Model Powered Dialogue Agents, Yang Deng, Wenxuan Zhang, Wai Lam, See-Kiong Ng, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Proactive dialogues serve as a practical yet challenging dialogue problem in the era of large language models (LLMs), where the dialogue policy planning is the key to improving the proactivity of LLMs. Most existing studies enable the dialogue policy planning of LLMs using various prompting schemes or iteratively enhance this capability in handling the given case with verbal AI feedback. However, these approaches are either bounded by the policy planning capability of the frozen LLMs or hard to be transferred to new cases. In this work, we introduce a new dialogue policy planning paradigm to strategize LLMs for proactive dialogue …

Intriguing Properties Of Data Attribution On Diffusion Models, Xiaosen Zheng, Tianyu Pang, Chao Du, Jing Jiang, Min Lin

Research Collection School Of Computing and Information Systems

Data attribution seeks to trace model outputs back to training data. With the recent development of diffusion models, data attribution has become a desired module to properly assign valuations for high-quality or copyrighted training samples, ensuring that data contributors are fairly compensated or credited. Several theoretically motivated methods have been proposed to implement data attribution, in an effort to improve the trade-off between computational scalability and effectiveness. In this work, we conduct extensive experiments and ablation studies on attributing diffusion models, specifically focusing on DDPMs trained on CIFAR-10 and CelebA, as well as a Stable Diffusion model LoRA-finetuned on ArtBench. …

Reinforcement Retrieval Leveraging Fine-Grained Feedback For Fact Checking News Claims With Black-Box Llm, Xuan Zhang, Wei Gao

Research Collection School Of Computing and Information Systems

Retrieval-augmented language models have exhibited promising performance across various areas of natural language processing (NLP), including fact-critical tasks. However, due to the black-box nature of advanced large language models (LLMs) and the non-retrieval-oriented supervision signal of specific tasks, the training of retrieval model faces significant challenges under the setting of black-box LLM. We propose an approach leveraging Fine-grained Feedback with Reinforcement Retrieval (FFRR) to enhance fact-checking on news claims by using black-box LLM. FFRR adopts a two-level strategy to gather fine-grained feedback from the LLM, which serves as a reward for optimizing the retrieval policy, by rating the retrieved documents …

On The Feasibility Of Simple Transformer For Dynamic Graph Modeling, Yuxia Wu, Yuan Fang, Lizi Liao

Research Collection School Of Computing and Information Systems

Dynamic graph modeling is crucial for understanding complex structures in web graphs, spanning applications in social networks, recommender systems, and more. Most existing methods primarily emphasize structural dependencies and their temporal changes. However, these approaches often overlook detailed temporal aspects or struggle with long-term dependencies. Furthermore, many solutions overly complicate the process by emphasizing intricate module designs to capture dynamic evolutions. In this work, we harness the strength of the Transformer’s self-attention mechanism, known for adeptly handling long-range dependencies in sequence modeling. Our approach offers a simple Transformer model, called SimpleDyG, tailored for dynamic graph modeling without complex modifications. We …

Text-Attributed Graph Representation Learning : Methods, Applications, And Challenges, Ce Zhang, Menglin Yang, Rex Ying, Hady Wirawan Lauw

Research Collection School Of Computing and Information Systems

Text documents are usually connected in a graph structure, resulting in an important class of data named text-attributed graph, e.g., paper citation graph and Web page hyperlink graph. On the one hand, Graph Neural Networks (GNNs) consider text in each document as general vertex attribute and do not specifically deal with text data. On the other hand, Pre-trained Language Models (PLMs) and Topic Models (TMs) learn effective document embeddings. However, most models focus on text content in each single document only, ignoring link adjacency across documents. The above two challenges motivate the development of text-attributed graph representation learning, combining GNNs …

Automatic Grading Of Short Answers Using Large Language Models In Software Engineering Courses, Nguyen Binh Duong Ta, Yi Meng Chai

Research Collection School Of Computing and Information Systems

Short-answer based questions have been used widely due to their effectiveness in assessing whether the desired learning outcomes have been attained by students. However, due to their open-ended nature, many different answers could be considered entirely or partially correct for the same question. In the context of computer science and software engineering courses where the enrolment has been increasing recently, manual grading of short-answer questions is a time-consuming and tedious process for instructors. In software engineering courses, assessments concern not just coding but many other aspects of software development such as system analysis, architecture design, software processes and operation methodologies …

Sequential Recommendation: From Representation Learning To Reasoning, Lei Wang

Dissertations and Theses Collection (Open Access)

The recommender system is a crucial component of today's online services. It helps users navigate through an overwhelmingly large number of items and discovering those that interest them. Unlike general recommender systems, which recommend items based on the user's overall preferences, sequential recommender systems consider the order of user-item interactions. Sequential recommendations aim to predict the next item a user will interact with, given a sequence of previously interacted items, while considering the short-term and long-term dependencies among items.

In this thesis, we focus on sequential recommendation methods: from representation learning to large language model (LLM)-based reasoning. On the one …

The Important Role Of System Dynamics Investigation On Business Model, Industry And Performance Management, Lina Gozali, Teuku Yuri M. Zagloel, Togar Mangihut Simatupang, Wahyudi Sutopo, Aldy Gunawan, Yun-Chia Liang, Bernardo Nugroho Yahya, Jose Arturo Garza-Reyes, Agustinus Purna Irawan, Yuliani Suseno

Research Collection School Of Computing and Information Systems

Purpose: This research studies the development of the evolving dynamic system model and explores the important elements or factors and what detailed attributes are the main influences model in achieving the success of a business, industry and management. It also identifies the real and major differences between static and dynamic business management models and the detailed factors that influence them. Later, this research investigates the benefits/advantages and limitations/disadvantages of some research studies. The studies conducted in this research put more emphasis on the capabilities of system dynamics (SD) in modeling and the ability to measure, analyse and capture problems in …

Enhancing Source Code Representations For Deep Learning With Static Analysis, Xueting Guan, Christoph Treude

Research Collection School Of Computing and Information Systems

Deep learning techniques applied to program analysis tasks such as code classification, summarization, and bug detection have seen widespread interest. Traditional approaches, however, treat programming source code as natural language text, which may neglect significant structural or semantic details. Additionally, most current methods of representing source code focus solely on the code, without considering beneficial additional context. This paper explores the integration of static analysis and additional context such as bug reports and design patterns into source code representations for deep learning models. We use the Abstract Syntax Tree-based Neural Network (ASTNN) method and augment it with additional context information …

Assessing Ai Detectors In Identifying Ai-Generated Code: Implications For Education, Wei Hung Pan, Ming Jie Chok, Jonathan Leong Shan Wong, Yung Xin Shin, Yeong Shian Poon, Zhou Yang, Chun Yong Chong, David Lo, Mei Kuan Lim

Research Collection School Of Computing and Information Systems

Educators are increasingly concerned about the usage of Large Language Models (LLMs) such as ChatGPT in programming education, particularly regarding the potential exploitation of imperfections in Artificial Intelligence Generated Content (AIGC) Detectors for academic misconduct.In this paper, we present an empirical study where the LLM is examined for its attempts to bypass detection by AIGC Detectors. This is achieved by generating code in response to a given question using different variants. We collected a dataset comprising 5,069 samples, with each sample consisting of a textual description of a coding problem and its corresponding human-written Python solution codes. These samples were …

Implementation And Evaluation Of Ai-Based Citizen Question-Answer Recommender (Acqar) To Enhance Citizen Service Delivery In Singapore Public Sector: A Case Study, Hui Shan Lee

Dissertations and Theses Collection (Open Access)

Government agencies prioritize citizen service delivery to foster trust with the public. Technological advancements, particularly in Artificial Intelligence (AI), hold promise for improving service provision and aligning government operations with citizens' needs. Yet the inherent inflexibility of Service Level Agreements (SLAs) often overlooks the nuances of human emotions and the varied nature of citizen inquiries, exacerbated by a lack of tools to guide appropriate responses. This dissertation aims to address the gaps of overlook of human emotions and non-support for appropriate responses, by exploring the following questions: (1) Can a predictive model incorporating both numeric and textual data effectively forecast …

From The Editors: Mobilizing New Sources Of Data: Opportunities And Recommendations, Denis A. Gregoire, Anne L. J. Ter Wal, Laura M. Little, Sekou Bermiss, Reddi Kotha, Marc Gruber

Research Collection Lee Kong Chian School Of Business

In June 2008, the U.S.-based website Glassdoor.com began posting anonymous company reviews and salary data from current and former employees of various organizations. Doing so not only brought to the world information that had hitherto been restricted to private circles, it spontaneously prompted some organizations to alter their workplace practices (Dineen & Allen, 2016; Dube & Zhu, 2021). At the same time, Glassdoor’s very activities gave rise to a completely new source of data for exploring a wealth of management and organizational phenomena (e.g., Bermiss & McDonald, 2018; Rhee, 2024). As this example illustrates, new data sources can not only …

Classifying Source Code: How Far Can Compressor-Based Classifiers Go?, Zhou Yang

Research Collection School Of Computing and Information Systems

Pre-trained language models of code, which are built upon large-scale datasets, millions of trainable parameters, and high computational resources cost, have achieved phenomenal success. Recently, researchers have proposed a compressor-based classifier (Cbc); it trains no parameters but is found to outperform BERT. We conduct the first empirical study to explore whether this lightweight alternative can accurately classify source code. Our study is more than applying Cbc to code-related tasks. We first identify an issue that the original implementation overestimates Cbc. After correction, Cbc's performance on defect prediction drops from 80.7% to 63.0%, which is still comparable to CodeBERT (63.7%). We …

Creative And Correct: Requesting Diverse Code Solutions From Ai, Scott Blyth, Markus Wagner, Christoph Treude

Research Collection School Of Computing and Information Systems

AI foundation models have the capability to produce a wide array of responses to a single prompt, a feature that is highly beneficial in software engineering to generate diverse code solutions. However, this advantage introduces a significant trade-off between diversity and correctness. In software engineering tasks, diversity is key to exploring design spaces and fostering creativity, but the practical value of these solutions is heavily dependent on their correctness. Our study systematically investigates this trade-off using experiments with HumanEval tasks, exploring various parameter settings and prompting strategies. We assess the diversity of code solutions using similarity metrics from the code …

Large Language Model For Vulnerability Detection: Emerging Results And Future Directions, Xin Zhou, Ting Zhang, David Lo

Research Collection School Of Computing and Information Systems

Previous learning-based vulnerability detection methods relied on either medium-sized pre-trained models or smaller neural networks from scratch. Recent advancements in Large Pre-Trained Language Models (LLMs) have showcased remarkable few-shot learning capabilities in various tasks. However, the effectiveness of LLMs in detecting software vulnerabilities is largely unexplored. This paper aims to bridge this gap by exploring how LLMs perform with various prompts, particularly focusing on two state-of-the-art LLMs: GPT-3.5 and GPT-4. Our experimental results showed that GPT-3.5 achieves competitive performance with the prior state-of-the-art vulnerability detection approach and GPT-4 consistently outperformed the state-of-the-art.

Exploring The Potential Of Chatgpt In Automated Code Refinement: An Empirical Study, Qi Guo, Shangqing Liu, Junming Cao, Xiaohong Li, Xin Peng, Xiaofei Xie, Bihuan Chen

Research Collection School Of Computing and Information Systems

Code review is an essential activity for ensuring the quality and maintainability of software projects. However, it is a time-consuming and often error-prone task that can significantly impact the development process. Recently, ChatGPT, a cutting-edge language model, has demonstrated impressive performance in various natural language processing tasks, suggesting its potential to automate code review processes. However, it is still unclear how well ChatGPT performs in code review tasks. To fill this gap, in this paper, we conduct the first empirical study to understand the capabilities of ChatGPT in code review tasks, specifically focusing on automated code refinement based on given …

Improving Automated Code Reviews: Learning From Experience, Hong Yi Lin, Patanamon Thongtanunam, Christoph Treude, Wachiraphan Charoenwet

Research Collection School Of Computing and Information Systems

Modern code review is a critical quality assurance process that is widely adopted in both industry and open source software environments. This process can help newcomers learn from the feedback of experienced reviewers; however, it often brings a large workload and stress to reviewers. To alleviate this burden, the field of automated code reviews aims to automate the process, teaching large language models to provide reviews on submitted code, just as a human would. A recent approach pre-trained and fine-tuned the code intelligent language model on a large-scale code review corpus. However, such techniques did not fully utilise quality reviews …

Exploring The Potential Of Chatgpt In Automated Code Refinement: An Empirical Study, Guo Qi, Junming Cao, Xiaofei Xie, Shangqing Liu, Xiaohong Li, Bihuan Chen, Xin Peng

Research Collection School Of Computing and Information Systems

Code review is an essential activity for ensuring the quality and maintainability of software projects. However, it is a time-consuming and often error-prone task that can significantly impact the development process. Recently, ChatGPT, a cutting-edge language model, has demonstrated impressive performance in various natural language processing tasks, suggesting its potential to automate code review processes. However, it is still unclear how well ChatGPT performs in code review tasks. To fill this gap, in this paper, we conduct the first empirical study to understand the capabilities of ChatGPT in code review tasks, specifically focusing on automated code refinement based on given …

Hop‑Based Heterogeneous Graph Transformer, Zixuan Yang, Xiao Wang, Yanhua Yu, Yuling Wang, Kangkang Lu, Zirui Guo, Xiting Qin, Yunshan Ma, Tat‑Seng Chua

Research Collection School Of Computing and Information Systems

The Graph Transformer (GT) has shown significant ability in processing graph-structured data, addressing limitations in graph neural networks, such as over-smoothing and over-squashing. However, the implementation of GT in real-world heterogeneous graphs (HGs) with complex topology continues to present numerous challenges. Firstly, a challenge arises in designing a tokenizer that is compatible with heterogeneity. Secondly, the complexity of the transformer hampers the acquisition of high-order neighbor information in HGs. In this paper, we propose a novel Hop-basedHeterogeneous Graph Transformer (H2Gormer) framework, paving a promising path for HGs to benefit from the capabilities of Transformers. We propose a Heterogeneous Hop-based Token …

Discovering Significant Topics From Legal Decisions With Selective Inference, Jerrold Tsin Howe Soh

Research Collection Yong Pung How School Of Law

We propose and evaluate an automated pipeline for discovering significant topics from legal decision texts by passing features synthesized with topic models through penalized regressions and post-selection significance tests. The method identifies case topics significantly correlated with outcomes, topic-word distributions which can be manually interpreted to gain insights about significant topics, and case-topic weights which can be used to identify representative cases for each topic. We demonstrate the method on a new dataset of domain name disputes and a canonical dataset of European Court of Human Rights violation cases. Topic models based on latent semantic analysis as well as language …

Screening Through A Broad Pool: Towards Better Diversity For Lexically Constrained Text Generation, Changsen Yuan, Heyan Huang, Yixin Cao, Qianwen Cao

Research Collection School Of Computing and Information Systems

Lexically constrained text generation (CTG) is to generate text that contains given constrained keywords. However, the text diversity of existing models is still unsatisfactory. In this paper, we propose a lightweight dynamic refinement strategy that aims at increasing the randomness of inference to improve generation richness and diversity while maintaining a high level of fluidity and integrity. Our basic idea is to enlarge the number and length of candidate sentences in each iteration, and choose the best for subsequent refinement. On the one hand, different from previous works, which carefully insert one token between two words per action, we insert …

Leveraging Multimodal Features And Item‑Level User Feedback For Bundle Construction, Yunshan Ma, Xiaohao Liu, Yinwei Wei, Zhulin Tao, Xiang Wang, Tat‑Seng Chua

Research Collection School Of Computing and Information Systems

Automatic bundle construction is a crucial prerequisite step in various bundle-aware online services. Previous approaches are mostly designed to model the bundling strategy of existing bundles. However, it is hard to acquire large-scale well-curated bundle dataset, especially for those platforms that have not offered bundle services before. Even for platforms with mature bundle services, there are still many items that are included in few or even zero bundles, which give rise to sparsity and cold-start challenges in the bundle construction models. To tackle these issues, we target at leveraging multimodal features, item-level user feedback signals, and the bundle composition information, …

Math Word Problem Generation Via Disentangled Memory Retrieval, Wei Qin, Xiaowei Wang, Zhenzhen Hu, Lei Wang, Yunshi Lan, Richang Hong

Research Collection Lee Kong Chian School Of Business

The task of math word problem (MWP) generation, which generates an MWP given an equation and relevant topic words, has increasingly attracted researchers’ attention. In this work, we introduce a simple memory retrieval module to search related training MWPs, which are used to augment the generation. To retrieve more relevant training data, we also propose a disentangled memory retrieval module based on the simple memory retrieval module. To this end, we first disentangle the training MWPs into logical description and scenario description and then record them in respective memory modules. Later, we use the given equation and topic words as …

Active Discovering New Slots For Task-Oriented Conversation, Yuxia Wu, Tianhao Dai, Zhedong Zheng, Lizi Liao

Research Collection School Of Computing and Information Systems

Existing task-oriented conversational systems heavily rely on domain ontologies with pre-defined slots and candidate values. In practical settings, these prerequisites are hard to meet, due to the emerging new user requirements and ever-changing scenarios. To mitigate these issues for better interaction performance, there are efforts working towards detecting out-of-vocabulary values or discovering new slots under unsupervised or semi-supervised learning paradigms. However, overemphasizing on the conversation data patterns alone induces these methods to yield noisy and arbitrary slot results. To facilitate the pragmatic utility, real-world systems tend to provide a stringent amount of human labeling quota, which offers an authoritative way …

Knowledge Generation For Zero-Shot Knowledge-Based Vqa, Rui Cao, Jing Jiang

Research Collection School Of Computing and Information Systems

Previous solutions to knowledge-based visual question answering (K-VQA) retrieve knowledge from external knowledge bases and use supervised learning to train the K-VQA model. Recently pre-trained LLMs have been used as both a knowledge source and a zero-shot QA model for K-VQA and demonstrated promising results. However, these recent methods do not explicitly show the knowledge needed to answer the questions and thus lack interpretability. Inspired by recent work on knowledge generation from LLMs for text-based QA, in this work we propose and test a similar knowledge-generation-based K-VQA method, which first generates knowledge from an LLM and then incorporates the generated …

T-Sciq: Teaching Multimodal Chain-Of-Thought Reasoning Via Large Language Model Signals For Science Question Answering, Lei Wang, Yi Hu, Jiabang He, Xing Xu, Ning Liu, Hui Liu, Heng Tao Shen

Research Collection School Of Computing and Information Systems

Large Language Models (LLMs) have recently demonstrated exceptional performance in various Natural Language Processing (NLP) tasks. They have also shown the ability to perform chain-of-thought (CoT) reasoning to solve complex problems. Recent studies have explored CoT reasoning in complex multimodal scenarios, such as the science question answering task, by fine-tuning multimodal models with high-quality human-annotated CoT rationales. However, collecting high-quality COT rationales is usually time-consuming and costly. Besides, the annotated rationales are hardly accurate due to the external essential information missed. To address these issues, we propose a novel method termed T-SciQ that aims at teaching science question answering with …

State Institutions In Northeast Thailand: Lao Ethnics And The Thai Identity, Jacob Ricks

Research Collection School of Social Sciences

In this last chapter on state representation, we focus on a case where there has been an absence of demands. In Northeast Thailand, the large ethnic Lao population has not demanded cultural concessions from the state. In fact, not only have the demands been absent, but most people in the region see themselves as Thai (the broader national identity) or Isan (a moniker meaning “northeast”)—as opposed to ethnically Lao. The absence of the Lao identity has less to do with the absence of civic associations from the bottom up than with the absence of political representation from the top down. …

Age And Ideology: The Emergence Of New Political Cleavages In Thailand’S 2566 (2023) Election, Napon Jatusripitak, Jacob Ricks

Research Collection School of Social Sciences

The Move Forward Party’s victory in Thailand’s 14 May 2566 (2023 CE) election surprised most observers, defying widespread predictions of a Pheu Thai win. Departing from traditional vote-mobilization strategies, Move Forward’s campaign focused largely on social media and broad calls for political reform while eschewing the vote-canvassing networks and economic policy promises that had delivered victory after victory for Pheu Thai. Does Move Forward’s win indicate changes in Thai voting behaviour? Relying on data from an original survey collected the week before and the week after the election, as well as observations from fieldwork, we identify two political cleavages that …