Digital Commons Network^™

Semantic Loss-Guided Data-Efficient Supervised Fine-Tuning For Safe Responses In Llms, Yuxiao Lu, Pradeep Varakantham, Pradeep Varakantham

Research Collection School Of Computing and Information Systems

Large Language Models (LLMs) generating unsafe responses to toxic prompts is a significant issue in their applications. While various efforts aim to address this safety concern, previous approaches often demand substantial human data collection or rely on the less dependable option of using another LLM to generate corrective data. In this paper, we aim to take this problem and overcome limitations of requiring significant high-quality human data. Our method requires only a small set of unsafe responses to toxic prompts, easily obtained from the unsafe LLM itself. By employing a semantic cost combined with a negative Earth Mover Distance (EMD) …

Can Llms Replace Manual Annotation Of Software Engineering Artifacts?, Toufique Ahmed, Premkumar Devanbu, Christoph Treude, Michael Pradel

Research Collection School Of Computing and Information Systems

Experimental evaluations of software engineering innovations, e.g., tools and processes, often include human-subject studies as a component of a multi-pronged strategy to obtain greater generalizability of the findings. However, human-subject studies in our field are challenging, due to the cost and difficulty of finding and employing suitable subjects, ideally, professional programmers with varying degrees of experience. Meanwhile, large language models (LLMs) have recently started to demonstrate human-level performance in several areas. This paper explores the possibility of substituting costly human subjects with much cheaper LLM queries in evaluations of code and code-related artifacts. We study this idea by applying six …

Chatcrs: Incorporating External Knowledge And Goal Guidance For Llm-Based Conversational Recommender Systems, Chuang Li, Yang Deng, Hengchang Hu, Min-Yen Kan, Haizhou Li

Research Collection School Of Computing and Information Systems

This paper aims to efficiently enable large language models (LLMs) to use external knowledge and goal guidance in conversational recommender system (CRS) tasks. Advanced LLMs (e.g., ChatGPT) are limited in domain-specific CRS tasks for 1) generating grounded responses with recommendation-oriented knowledge, or 2) proactively leading the conversations through different dialogue goals. In this work, we first analyze those limitations through a comprehensive evaluation, showing the necessity of external knowledge and goal guidance which contribute significantly to the recommendation accuracy and language quality. In light of this finding, we propose a novel ChatCRS framework to decompose the complex CRS task into …

Agentstudio: A Toolkit For Building General Virtual Agents, Longtao Zheng, Zhiyuan Huang, Zhenghai Xue, Xinrun Wang, Bo An, Shuicheng Yan

Research Collection School Of Computing and Information Systems

General virtual agents need to handle multimodal observations, master complex action spaces, and self-improve in dynamic, open-domain environments. However, existing environments are often domain-specific and require complex setups, which limits agent development and evaluation in real-world settings. As a result, current evaluations lack in-depth analyses that decompose fundamental agent capabilities. We introduce AgentStudio, a trinity of environments, tools, and benchmarks to address these issues. AgentStudio provides a lightweight, interactive environment with highly generic observation and action spaces, e.g., video observations and GUI/API actions. It integrates tools for creating online benchmark tasks, annotating GUI elements, and labeling actions in videos. Based …

Bigcodebench: Benchmarking Code Generation With Diverse Function Calls And Complex Instructions, T.Y. Zhuo, M.C. Vu, J. Chim, ..., David Lo

Research Collection School Of Computing and Information Systems

Task automation has been greatly empowered by the recent advances in Large Language Models (LLMs) via Python code, where the tasks ranging from software engineering development to general-purpose reasoning. While current benchmarks have shown that LLMs can solve tasks using programs like human developers, the majority of their evaluations are limited to short and self-contained algorithmic tasks or standalone function calls. Solving challenging and practical tasks requires the capability of utilizing diverse function calls as tools to efficiently implement functionalities like data analysis and web development. In addition, using multiple tools to solve a task needs compositional reasoning by accurately …

Graph Foundation Models: Concepts, Opportunities And Challenges, Jiawei Liu, Cheng Yang, Zhiyuan Lu, Junze Chen, Yibo Li, Mengmei Zhang, Ting Bai, Fang Yuan, Lichao Sun, Philip S. Yu, Chuan Shi

Research Collection School Of Computing and Information Systems

Foundation models have emerged as critical components in a variety of artificial intelligence applications, and showcase significant success in natural language processing and several other domains. Meanwhile, the field of graph machine learning is witnessing a paradigm transition from shallow methods to more sophisticated deep learning approaches. The capabilities of foundation models in generalization and adaptation motivate graph machine learning researchers to discuss the potential of developing a new graph learning paradigm. This paradigm envisions models that are pre-trained on extensive graph data and can be adapted for various graph tasks. Despite this burgeoning interest, there is a noticeable lack …

Reimagining Education: Keeping The Human In The Loop, Pradeep Varakantham, Sidney Tio

Asian Management Insights

How educators can work with generative artificial intelligence models to improve learning. Artificial intelligence (AI) helps break the mould of one-size-fits-all education by creating personalised learning paths that adapt to each student’s pace and style. By combining human expertise with AI capabilities, educators can create learning experiences that are both structured and flexible, thus getting the best of both worlds. While promising, AI used in educational contexts must carefully navigate privacy concerns, ensure fairness across all student groups, and support appropriate learning progression.

Law, Politics, And The Academy In Asia: Navigating Constraints As Public Law Scholars, De Maartje Visser, Qian Liu, Victor V. Ramraj

Research Collection Yong Pung How School Of Law

How do academics interested in the study of legal topics that implicate the state relate to and deal with pressures that shape the space available to conduct research? This article examines the nature and impact of such pressures on Asia-focused public law scholars who must contend with a more diverse socio-political environment than the liberal democratic setting in which questions of academic freedom are typically explored. We find that the Asia-centric academy is affected by a wide range of constraints that notably extends beyond intra-institutional demands to those put in place by the state. This article also highlights how the …

The Impact Of Marriage Status On Career Aspiration And Performance, Qiang Yi

Dissertations and Theses Collection (Open Access)

This study explores the impact of marital status on employee workplace behavior and job performance. Specifically, it finds that compared to unmarried employees, married employees demonstrate higher career aspirations and job performance. Further analysis reveals that this effect is primarily driven by the enhancement of family and career commitments brought about by marriage. These increased commitments significantly contribute to the improvement of employees' career aspirations and job performance. Moreover, this study examines the gender differences in the influence of marital status on family and career commitments.

The results show that marriage has a stronger effect on promoting family commitments among …

Retrieval Augmented Recipe Generation, Guoshan Liu, Hailong Yin, Bin Zhu, Jingjing Chen, Chong-Wah Ngo, Yu-Gang Jiang

Research Collection School Of Computing and Information Systems

The growing interest in generating recipes from food images has drawn substantial research attention in recent years. Existing works for recipe generation primarily utilize a two-stage training method—first predicting ingredients from a food image and then generating instructions from both the image and ingredients. Large Multi-modal Models (LMMs), which have achieved notable success across a variety of vision and language tasks, shed light on generating both ingredients and instructions directly from images. Nevertheless, LMMs still face the common issue of hallu- cinations during recipe generation, leading to suboptimal performance. To tackle this issue, we propose a retrieval augmented large multimodal …

A Contrastive Framework With User, Item And Review Alignment For Recommendation, Viet Hoang Dong, Yuan Fang, Hady Wirawan Lauw

Research Collection School Of Computing and Information Systems

Learning effective latent representations for users and items is the cornerstone of recommender systems. Traditional approaches rely on user-item interaction data to map users and items into a shared latent space, but the sparsity of interactions often poses challenges. While leveraging user reviews could mitigate this sparsity, existing review-aware recommendation models often exhibit two key limitations. First, they typically rely on reviews as additional features, but reviews are not universal, with many users and items lacking them. Second, such approaches do not integrate reviews into the useritem space, leading to potential divergence or inconsistency among user, item, and review representations. …

Neurovig: Integrating Event Cameras For Resource-Efficient Video Grounding, Dulanga Weerakoon, Vigneshwaran Subbaraju, Joo Hwee Lim, Archan Misra

Research Collection School Of Computing and Information Systems

Spatio-Temporal Video Grounding (STVG) - the task of identifying the target object in the field-of-view that the language instruction refers to - is a fundamental vision-language task. Current STVG approaches typically utilize feeds from an RGB camera that is assumed to be always-on and process the video frames using complex neural network pipelines. As a result they often impose prohibitive system overheads (energy latency) on pervasive devices. To address this we propose NeuroViG with two key innovations: (a) leveraging on event streams from a low-power neuromorphic event camera sensor to perform selective triggering of the more energy-hungry RGB camera for …

Explainable Neural Networks With Guarantees: A Sparse Estimation Approach, Antoine Ledent, Peng Liu

Research Collection School Of Computing and Information Systems

Balancing predictive power and interpretability has long been a challenging research area, particularly in powerful yet complex models like neural networks, where nonlinearity obstructs direct interpretation. This paper introduces a novel approach to constructing an explainable neural network that harmonizes predictiveness and explainability. Our model is designed as a linear combination of a sparse set of jointly learned features, each derived from a different trainable function applied to a single 1-dimensional input feature. Leveraging the ability to learn arbitrarily complex relationships, our neural network architecture enables automatic selection of a sparse set of important features, with the final prediction being …

Multisfl: Towards Accurate Split Federated Learning Via Multi-Model Aggregation And Knowledge Replay, Zeke Xia, Ming Hu, Dengke Yan, Ruixuan Liu, Anran Li, Xiaofei Xie, Mingsong Chen

Research Collection School Of Computing and Information Systems

Although Split Federated Learning (SFL) effectively enables knowledge sharing among resource-constrained clients, it suffers from low training performance due to the neglect of data heterogeneity and catastrophic forgetting problems. To address these issues, we propose a novel SFL approach named MultiSFL, which adopts i) an effective multimodel aggregation mechanism to alleviate gradient divergence caused by heterogeneous data and ii) a novel knowledge replay strategy to deal with the catastrophic forgetting problem. MultiSFL adopts two servers (i.e., the fed server and main server) to maintain multiple branch models for local training and an aggregated master model for knowledge sharing among branch …

Lightprof: A Lightweight Reasoning Framework For Large Language Model On Knowledge Graph, Tu Ao, Yanhua Yu, Yuling Wang, Yang Deng, Zirui Guo, Liang Pang, Pinghui Wang, Tat-Seng Chua, Xiao Zhang, Zhen Cai

Research Collection School Of Computing and Information Systems

Large Language Models (LLMs) have impressive capabilities in text understanding and zero-shot reasoning. However, delays in knowledge updates may cause them to reason incorrectly or produce harmful results. Knowledge Graphs (KGs) provide rich and reliable contextual information for the reasoning process of LLMs by structurally organizing and connecting a wide range of entities and relations. Existing KG-based LLM reasoning methods only inject KGs’ knowledge into prompts in a textual form, ignoring its structural information. Moreover, they mostly rely on close-source models or open-source models with large parameters, which poses challenges to high resource consumption. To address this, we propose a …

Aligning Large Language Models For Faithful Integrity Against Opposing Argument, Yong Zhao, Yang Deng, See-Kiong Ng, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Large Language Models (LLMs) have demonstrated impressive capabilities in complex reasoning tasks. However, they can be easily misled by unfaithful arguments during conversations, even when their original statements are correct. To this end, we investigate the problem of maintaining faithful integrity in LLMs. This involves ensuring that LLMs adhere to their faithful statements in the face of opposing arguments and are able to correct their incorrect statements when presented with faithful arguments. In this work, we propose a novel framework, named Alignment for Faithful Integrity with Confidence Estimation (AFICE), which aims to align the LLM responses with faithful integrity. Specifically, …

Learning To Identify Seen, Unseen And Unknown In The Open World: A Practical Setting For Zero-Shot Learning, Sethupathy Parameswaran, Yuan Fang, Chandan Gautam, Savitha Ramasamy, Xiaoli Li

Research Collection School Of Computing and Information Systems

As vision-language models advance, addressing the Zero-Shot Learning (ZSL) problem in the open world becomes increasingly crucial. Specifically, a robust model must handle three types of samples during inference: seen classes with visual and semantic information provided in training, unseen classes with only the semantic information in training, and unknown samples with no prior information from training. Existing methods either handle seen and unseen classes together (ZSL) or seen and unknown classes (known as Open-Set Recognition, OSR). However, none addresses the simultaneous handling of all three, which we term Open-Set Zero-Shot Learning (OZSL). To address this problem, we propose a …

Attention To Market Expansion: Aspirational Antecedent And Risk-Taking Consequence, Renfei Gao, Man Zhang, Xiaogang He, Zhengyu Li

Research Collection Lee Kong Chian School Of Business

The behavioral theory of the firm (BTOF) emphasizes the goal-directed logic in explaining firms’ risk-taking.Scholars in this tradition typically conceptualize how performance feedback indicates problems and triggers risk-taking behaviors. Yet, the theory remains underdeveloped in understanding decision-makers’ attention to forward-looking goals, such as market expansion, and its impact on firm risk-taking. In this study, we theorize performance feedback as an antecedent to decision-makers’ attention to forward-looking goals, and firm risktaking as a consequence of such attention. Focusing on market expansion as a critical forward-looking goal, we first theorize how performance feedback influences decision-makers’ attention to market expansion. Then, we examine …

Adapting Knowledge Prompt Tuning For Enhanced Automated Program Repair, Xuemeng Cai, Lingxiao Jiang

Research Collection School Of Computing and Information Systems

Automated Program Repair (APR) aims to enhance software reliability by automatically generating bug-fixing patches. Recent work has improved the state-of-the-art of APR by fine-tuning pre-trained large language models (LLMs), such as CodeT5, for APR. However, the effectiveness of fine-tuning be-comes weakened in data scarcity scenarios, and data scarcity can be a common issue in practice, limiting fine-tuning performance. To alleviate this limitation, this paper adapts prompt tuning for enhanced APR and conducts a comprehensive study to evaluate its effectiveness in data scarcity scenarios, using three LLMs of different sizes and six diverse datasets across four programming languages. Prompt tuning rewrites …

Mimic: Ai And Ar-Enhanced Multi-Modal, Immersive, Relative Instruction Comprehension, Dhanuja Wanniarachchi, Archan Misra

Research Collection School Of Computing and Information Systems

We present a multimodal instruction comprehension framework, called MImIC, that utilizes visual sensing (including LIDAR and 2D RGB sensing) & AI spatial reasoning capabilities to support more seamless and immersive interaction between humans and AI-driven situated assistive agents. MImIC's key new capability is to support disambiguation of a wider set of relative spatial references that users naturally employ while issuing spatially-situated instructions. To support enhanced visual grounding via a combination of both fully-qualified and relative attribute references, MImIC uses (a) a fine-tuned transformer-based language translation DNN to accurately convert natural verbal commands into a structured set of machine understandable constraints …

Explainable Neural Networks With Guarantee: A Sparse Estimation Approach, Antoine Ledent, Peng Liu

Research Collection School Of Computing and Information Systems

Balancing predictive power and interpretability has long been a challenging research area, particularly in powerful yet complex models like neural networks, where nonlinearity obstructs direct interpretation. This paper introduces a novel approach to constructing an explainable neural network that harmonizes predictiveness and explainability. Our model is designed as a linear combination of a sparse set of jointly learned features, each derived from a different trainable function applied to a single 1-dimensional input feature. Leveraging the ability to learn arbitrarily complex relationships, our neural network architecture enables automatic selection of a sparse set of important features, with the final prediction being …

Varium: Variational Autoencoder For Multi-Interest Representation With Inter-User Memory, Nhu Thuat Tran, Hady W. Lauw

Research Collection School Of Computing and Information Systems

Frameworks for discovering multiple user interest factors based on Variational AutoEncoder (VAE) has demonstrated competitive recommendation performance. However, as VAE only considers one user as input at a time, sharing across like-minded users may not be adequately facilitated. Moreover, interest sharing between users is not always available and thus, poses a challenge for VAE to explicitly model this information. To resolve this, we introduce an inter-user memory-based mechanism to unsupervisedly discover latent interest sharing between users under VAE framework. Concretely, we design a memory including an array of prototypes, each hypothetically representing a group of users sharing a particular interest. …

Simulation-Free Hierarchical Latent Policy Planning For Proactive Dialogues, Tao He, Lizi Liao, Yixin Cao, Yuanxing Liu, Yiheng Sun, Zerui Chen, Ming Liu, Bing Qin

Research Collection School Of Computing and Information Systems

Recent advancements in proactive dialogues have garnered significant attention, particularly for more complex objectives (e.g. emotion support and persuasion). Unlike traditional task-oriented dialogues, proactive dialogues demand advanced policy planning and adaptability, requiring rich scenarios and comprehensive policy repositories to develop such systems. However, existing approaches tend to rely on Large Language Models (LLMs) for user simulation and online learning, leading to biases that diverge from realistic scenarios and result in suboptimal efficiency. Moreover, these methods depend on manually defined, context-independent, coarse-grained policies, which not only incur high expert costs but also raise concerns regarding their completeness. In our work, we …

Evaluating Software Development Agents: Patch Patterns, Code Quality, And Issue Complexity In Real-World Github Scenarios, Zhi Chen, Lingxiao Jiang

Research Collection School Of Computing and Information Systems

In recent years, AI-based software engineering has progressed from pre-trained models to advanced agentic workflows, with Software Development Agents representing the next major leap. These agents, capable of reasoning, planning, and interacting with external environments, offer promising solutions to complex software engineering tasks. However, while much research has evaluated code generated by large language models (LLMs), comprehensive studies on agent-generated patches, particularly in real-world settings, are lacking. This study addresses that gap by evaluating 4,892 patches from 10 top-ranked agents on 500 real-world GitHub issues from SWE-Bench Verified, focusing on their impact on code quality. Our analysis shows no single …

Backdoor Token Unlearning: Exposing And Defending Backdoors In Pretrained Language Models, Peihai Jiang, Xixiang Lyu, Yige Li, Jing Ma

Research Collection School Of Computing and Information Systems

Supervised fine-tuning has become the predominant method for adapting large pretrained models to downstream tasks. However, recent studies have revealed that these models are vulnerable to backdoor attacks, where even a small number of malicious samples can successfully embed backdoor triggers into the model. While most existing defense methods focus on post-training backdoor defense, efficiently defending against backdoor attacks during training phase remains largely unexplored. To address this gap, we propose a novel defense method called Backdoor Token Unlearning (BTU), which proactively detects and neutralizes trigger tokens during the training stage. Our work is based on two key findings: 1) …

Revisiting Sentiment Analysis For Software Engineering In The Era Of Large Language Models, Ting Zhang, Ivana Clairine Irsan, Thung Ferdian, David Lo

Research Collection School Of Computing and Information Systems

Software development involves collaborative interactions where stakeholders express opinions across various platforms. Recognizing the sentiments conveyed in these interactions is crucial for the effective development and ongoing maintenance of software systems. For software products, analyzing the sentiment of user feedback, e.g., reviews, comments, and forum posts can provide valuable insights into user satisfaction and areas for improvement. This can guide the development of future updates and features. However, accurately identifying sentiments in software engineering datasets remains challenging.This study investigates bigger large language models (bLLMs) in addressing the labeled data shortage that hampers fine-tuned smaller large language models (sLLMs) in software …

An Aspect Performance-Aware Hypergraph Neural Network For Review-Based Recommendation, Junrui Liu, Tong Li, Di Wu, Zifang Tang, Yuan Fang, Zhen Yang

Research Collection School Of Computing and Information Systems

Online reviews allow consumers to provide detailed feedback on various aspects of items. Existing methods utilize these aspects to model users' fine-grained preferences for specific item features through graph neural networks. We argue that the performance of items on different aspects is important for making precise recommendations, which has not been taken into account by existing approaches, due to lack of data. In this paper, we propose an aspect performance-aware hypergraph neural network (APH) for the review-based recommendation, which learns the performance of items from the conflicting sentiment polarity of user reviews. Specifically, APH comprehensively models the relationships among users, …

Exploring & Exploiting High-Order Graph Structure For Sparse Knowledge Graph Completion, Tao He, Ming Liu, Yixin Cao, Zekun Wang, Zihao Zheng, Bing Qin

Research Collection School Of Computing and Information Systems

Sparse Knowledge Graph (KG) scenarios pose a challenge for previous Knowledge Graph Completion (KGC) methods, that is, the completion performance decreases rapidly with the increase of graph sparsity. This problem is also exacerbated because of the widespread existence of sparse KGs in practical applications. To alleviate this challenge, we present a novel framework, LR-GCN, that is able to automatically capture valuable long-range dependency among entities to supplement insufficient structure features and distill logical reasoning knowledge for sparse KGC. The proposed approach comprises two main components: a GNN-based predictor and a reasoning path distiller. The reasoning path distiller explores high-order graph …

A Causality-Aware Paradigm For Evaluating Creativity Of Multimodal Large Language Models, Zhongzhan Huang, Shanshan Zhong, Pan Zhou, Shanghua Gao, Marink Zitnik, Liang Lin

Research Collection School Of Computing and Information Systems

Recently, numerous benchmarks have been developed to evaluate the logical reasoning abilities of large language models (LLMs). However, assessing the equally important creative capabilities of LLMs is challenging due to the subjective, diverse, and data-scarce nature of creativity, especially in multimodal scenarios. In this paper, we consider the comprehensive pipeline for evaluating the creativity of multimodal LLMs, with a focus on suitable evaluation platforms and methodologies. First, we find the Oogiri game—a creativity-driven task requiring humor, associative thinking, and the ability to produce unexpected responses to text, images, or both. This game aligns well with the input-output structure of modern …

Seven Hci Grand Challenges Revisited: Five-Year Progress, Constantine Stephanidis, Gavriel Salvendy, Margherita Antona, Vincent G Duffy, Qin Gao, Waldemar Karwowski, Fiona Nah, Stavroula Ntoa, Pei-Luen Patrick Rau, Keng Siau, Jia Zhou

Research Collection School Of Computing and Information Systems

Motivated by the rapid technological advancements achieved in the last five years, and the pervasiveness of Artificial Intelligence, the paper investigates the evolving role of Human-Computer Interaction and revisits the seven grand challenges outlined in 2019: human-technology symbiosis, human-environment interactions, ethics, privacy and security, well-being, health and eudaimonia, accessibility and universal access, learning and creativity, and social organization and democracy. Through literature analysis, the paper reevaluates the status of each challenge and highlights emerging requirements. Key findings reveal the widespread impact of Artificial Intelligence across all domains and emphasize the need for improved AI transparency, alignment with human values, and …