Digital Commons Network^™

Empathyear : An Open-Source Avatar Multimodal Empathetic Chatbot, Hao Fei, Han Zhang, Bin Wang, Lizi Liao, Qian Liu, Erik Cambria

Research Collection School Of Computing and Information Systems

This paper introduces EmpathyEar, a pioneering open-source, avatar-based multimodal empathetic chatbot, to fill the gap in traditional text-only empathetic response generation (ERG) systems. Leveraging the advancements of a large language model, combined with multimodal encoders and generators, EmpathyEar supports user inputs in any combination of text, sound, and vision, and produces multimodal empathetic responses, offering users, not just textual responses but also digital avatars with talking faces and synchronized speeches. A series of emotion-aware instruction-tuning is performed for comprehensive emotional understanding and generation capabilities. In this way, EmpathyEar provides users with responses that achieve a deeper emotional resonance, closely emulating …

Clamber: A Benchmark Of Identifying And Clarifying Ambiguous Information Needs In Large Language Models, Tong Zhang, Peixin Qin, Yang Deng, Chen Huang, Wenqiang Lei, Junhong Liu, Dingnan Jin, Hongru Liang, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Large language models (LLMs) are increasingly used to meet user information needs, but their effectiveness in dealing with user queries that contain various types of ambiguity remains unknown, ultimately risking user trust and satisfaction. To this end, we introduce CLAMBER, a benchmark for evaluating LLMs using a well-organized taxonomy. Building upon the taxonomy, we construct 12K high-quality data to assess the strengths, weaknesses, and potential risks of various off-the-shelf LLMs.Our findings indicate the limited practical utility of current LLMs in identifying and clarifying ambiguous user queries, even enhanced by chain-of-thought (CoT) and few-shot prompting. These techniques may result in overconfidence …

Unified Training Of Universal Time Series Forecasting Transformers, Gerald Woo, Chenghao Liu, Akshat Kumar, Caiming Xiong, Silvio Savarese, Doyen Sahoo

Research Collection School Of Computing and Information Systems

Deep learning for time series forecasting has traditionally operated within a one-model-per-dataset framework, limiting its potential to leverage the game-changing impact of large pre-trained models. The concept of universal forecasting, emerging from pre-training on a vast collection of time series datasets, envisions a single Large Time Series Model capable of addressing diverse downstream forecasting tasks. However, constructing such a model poses unique challenges specific to time series data: i) cross-frequency learning, ii) accommodating an arbitrary number of variates for multivariate time series, and iii) addressing the varying distributional properties inherent in large-scale data. To address these challenges, we present novel …

Creating And Delivering Audio Descriptions For Videos, Rosiana Natalie

Dissertations and Theses Collection (Open Access)

Despite anti-discrimination regulations mandating the provision of audio descriptions (ADs), the majority of online video content remains inaccessible to blind and low-vision (BLV) individuals. This is because these ADs are either absent or fail to adequately address the diverse and unique needs of the audience. Traditionally, content creators have relied on professionals to author ADs. However, this gold standard may not be accessible for some content creators because this method is still costly and has a long turnaround time. Moreover, when ADs are available, they tend to be static and unalterable, failing to cater to the unique preferences of BLV …

How People Prompt Generative Ai To Create Interactive Vr Scenes, Setareh Aghel Manesh, Tianyi Zhang, Yuki Onishi, Kotaro Hara, Scott Bateman, Jiannan Li, Anthony Tang

Research Collection School Of Computing and Information Systems

Generative AI tools can provide people with the ability to create virtual environments and scenes with natural language prompts. Yet, how people will formulate such prompts is unclear---particularly when they inhabit the environment that they are designing. For instance, it is likely that a person might say, "Put a chair here,'' while pointing at a location. If such linguistic and embodied features are common to people's prompts, we need to tune models to accommodate them. In this work, we present a Wizard of Oz elicitation study with 22 participants, where we studied people's implicit expectations when verbally prompting such programming …

Towards Human-Centered Proactive Conversational Agents, Yang Deng, Lizi Liao, Zhonghua Zheng, Grace Hui Yang, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Recent research on proactive conversational agents (PCAs) mainly focuses on improving the system's capabilities in anticipating and planning action sequences to accomplish tasks and achieve goals before users articulate their requests. This perspectives paper highlights the importance of moving towards building human-centered PCAs that emphasize human needs and expectations, and that considers ethical and social implications of these agents, rather than solely focusing on technological capabilities. The distinction between a proactive and a reactive system lies in the proactive system's initiative-taking nature. Without thoughtful design, proactive systems risk being perceived as intrusive by human users. We address the issue by …

Transformer Models With Explainability For It Telemetry And Business Events, Shiau Hong Lim, Laura Wynter

Research Collection School Of Computing and Information Systems

Temporal event data are commonly encountered in software applications across a wide range of domains, from IT telemetry and system logs to business process automation. Temporal event data in software applications carry information in various forms: both structured and unstructured, and with both regular and irregular occurrence frequency, making the representation of temporal event data challenging. Further chal-lenges come from the diversity in terms of the scale and volume of events that need to be summarized by the representation. We propose a general and unified approach to handle temporal event data for the purpose of learning a predictive transformer model. …

Broadening The View: Demonstration-Augmented Prompt Learning For Conversational Recommendation, Quang Huy Dao, Yang Deng, Dung D. Le, Lizi Liao

Research Collection School Of Computing and Information Systems

Conversational Recommender Systems (CRSs) leverage natural language dialogues to provide tailored recommendations. Traditional methods in this field primarily focus on extracting user preferences from isolated dialogues. It often yields responses with a limited perspective, confined to the scope of individual conversations. Recognizing the potential in collective dialogue examples, our research proposes an expanded approach for CRS models, utilizing selective analogues from dialogue histories and responses to enrich both generation and recommendation processes. This introduces significant research challenges, including: (1) How to secure high-quality collections of recommendation dialogue exemplars? (2) How to effectively leverage these exemplars to enhance CRS models?To tackle …

Comparative Analysis Of Hate Speech Detection: Traditional Vs. Deep Learning Approaches, Haibo Pen, Nicole Anne Huiying Teo, Zhaoxia Wang

Research Collection School Of Computing and Information Systems

Detecting hate speech on social media poses a significant challenge, especially in distinguishing it from offensive language, as learning-based models often struggle due to nuanced differences between them, which leads to frequent misclassifications of hate speech instances, with most research focusing on refining hate speech detection methods. Thus, this paper seeks to know if traditional learning-based methods should still be used, considering the perceived advantages of deep learning in this domain. This is done by investigating advancements in hate speech detection. It involves the utilization of deep learning-based models for detailed hate speech detection tasks and compares the results with …

Combinatorial Creativity: Knowledge Graphs And Idea Generation In Crowdsourcing Innovation, Zhi Wei Vincent Mack

Dissertations and Theses Collection (Open Access)

This dissertation explores the dynamic interplay between combinatorial creativity and technology-driven innovation within various knowledge-intensive fields. It critically examines the role of combinatorial creativity in generating groundbreaking innovations by amalgamating existing ideas and technologies. This research incorporates a detailed examination of how knowledge, whether tacit or explicit, can be transformed into actionable data to foster innovation in crowdsourcing contexts. Chapter 2 provides an overview of the relevant literature on how Artificial Intelligence and Knowledge Management Systems can support combinatorial creativity. The study further delves into the transformative impact of knowledge management systems, particularly focusing on crowdsourcing platforms that leverage collective …

The Importance Of Theory And History In Understanding And Developing The Common Law Of Contract – Some Further Preliminary Reflections, Hon. Andrew Phang

Singapore Law Journal (Lexicon)

In a previous essay, an attempt was made to demonstrate the important role that both theory and history play in helping us to understand and develop the common law of contract. As pointed out in that essay, a comprehensive treatment of the subject would require lengthy discourse in a book or even several books. This essay follows-up on that previous essay, again by way of preliminary reflections only, to correct the dominant perception that the development of the common law in general and contract law in particular is premised mainly on doctrinal development based on logic and analogy with the …

Let’S Think Outside The Box: Exploring Leap-Of-Thought In Large Language Models With Multimodal Humor Generation, Shanshan Zhong, Zhongzhan Huang, Shanghua Gao, Wushao Wen, Liang Lin, Marinka Zitnik, Pan Zhou

Research Collection School Of Computing and Information Systems

Chain-of-Thought (CoT) [2, 3] guides large language models (LLMs) to reason step-by-step, and can motivate their logical reasoning ability. While effective for logical tasks, CoT is not conducive to creative problem-solving which often requires out-of-box thoughts and is crucial for innovation advancements. In this paper, we explore the Leap-of-Thought (LoT) abilities within LLMs — a nonsequential, creative paradigm involving strong associations and knowledge leaps. To this end, we study LLMs on the popular Oogiri game which needs participants to have good creativity and strong associative thinking for responding unexpectedly and humorously to the given image, text, or both, and thus …

Mix-Initiative Response Generation With Dynamic Prefix Tuning, Yuxiang Nie, Heyan Huang, Xian-Ling Mao, Lizi Liao

Research Collection School Of Computing and Information Systems

Mixed initiative serves as one of the key factors in controlling conversation directions. For a speaker, responding passively or leading proactively would result in rather different responses. However, most dialogue systems focus on training a holistic response generation model without any distinction among different initiatives. It leads to the cross-contamination problem, where the model confuses different initiatives and generates inappropriate responses. Moreover, obtaining plenty of human annotations for initiative labels can be expensive. To address this issue, we propose a general mix-Initiative Dynamic Prefix Tuning framework (IDPT) to decouple different initiatives from the generation model, which learns initiative-aware prefixes in …

Enhancing Code Vulnerability Detection Via Vulnerability-Preserving Data Augmentation, Shangqing Liu, Wei Ma, Jian Wang, Xiaofei Xie, Ruitao Feng, Yang Liu

Research Collection School Of Computing and Information Systems

Source code vulnerability detection aims to identify inherent vulnerabilities to safeguard software systems from potential attacks. Many prior studies overlook diverse vulnerability characteristics, simplifying the problem into a binary (0-1) classification task for example determining whether it is vulnerable or not. This poses a challenge for a single deep-learning based model to effectively learn the wide array of vulnerability characteristics. Furthermore, due to the challenges associated with collecting large-scale vulnerability data, these detectors often overfit limited training datasets, resulting in lower model generalization performance. To address the aforementioned challenges, in this work, we introduce a fine-grained vulnerability detector namely FGVulDet. …

Towards Faster Inference Of Transformers: Strategies For Accelerating Decoding Processes, Cunxiao Du

Dissertations and Theses Collection (Open Access)

This thesis delves into the acceleration and optimization of Transformer inference, a subject of increasing importance with the emergence of Large Language Models (LLMs). The study primarily addresses the challenges posed by two inherent properties of Transformers during inference: the quadratic complexity of the attention mechanism and the sequential nature of autoregressive inference. The research is structured into three main parts. The first part enhances the learning capabilities of non-autoregressive Transformers, achieving a remarkable 15.0x acceleration on machine translation tasks. The following section focuses on lossless acceleration through speculative decoding, where the proposed algorithm, Glide with CAPE, is shown to …

Anomaly Heterogeneity Learning For Open-Set Supervised Anomaly Detection, Jiawen Zhu, Choubo Ding, Yu Tian, Guansong Pang

Research Collection School Of Computing and Information Systems

Open-set supervised anomaly detection (OSAD) - a recently emerging anomaly detection area - aims at utilizing a few samples of anomaly classes seen during training to detect unseen anomalies (i.e., samples from open-set anomaly classes), while effectively identifying the seen anomalies. Benefiting from the prior knowledge illustrated by the seen anomalies, current OSAD methods can often largely reduce false positive errors. However, these methods are trained in a closed-set setting and treat the anomaly examples as from a homogeneous distribution, rendering them less effective in generalizing to unseen anomalies that can be drawn from any distribution. This paper proposes to …

Actively Learn From Llms With Uncertainty Propagation For Generalized Category Discovery, Jinggui Liang, Lizi Liao, Hao Fei, Bobo Li, Jing Jiang

Research Collection School Of Computing and Information Systems

Generalized category discovery faces a key issue: the lack of supervision for new and unseen data categories. Traditional methods typically combine supervised pretraining with self-supervised learning to create models, and then employ clustering for category identification. However, these approaches tend to become overly tailored to known categories, failing to fully resolve the core issue. Hence, we propose to integrate the feedback from LLMs into an active learning paradigm. Specifically, our method innovatively employs uncertainty propagation to select data samples from high-uncertainty regions, which are then labeled using LLMs through a comparison-based prompting scheme. This not only eases the labeling task …

What Drives Employers’ Favorability Ratings On Employer Review Platforms? The Role Of Symbolic, Personal, And Emotional Content, Christoph E. Höllig, Andranik Tumasjan, Filip Lievens

Research Collection Lee Kong Chian School Of Business

Employer review platforms have changed the recruitment landscape by allowing current and former employees to post messages about an employer outside of direct company control. Therefore, they have emerged as an important form of third-party employer branding. However, we know little about how such open-ended comments relate to the key variable in employer reviews: employers’ favorability rating. Therefore, we start by situating this variable among other constructs in the employer branding space. Next, we build theory on how content in the open-ended comments of an employer review relates to the positivity or negativity of the reviews’ favorability rating. We test …

Formal Versus Informal Supervisor Socio-Emotional Support Behaviours And Employee Trust: The Role Of Cultural Power Distance, Jaee Cho, S. Arzu Wasti, Krishna Savani, Hwee Hoon Tan, Michael W. Morris

Research Collection Lee Kong Chian School Of Business

This research investigates how formal versus informal supervisor support behaviours shape employees' affect- and cognition-based trust across cultures of varying power distance. Using data from in-depth interviews, Study 1 found that trust-enhancing supervisor behaviours were more formal, status conscious and imposing in India (a high power distance culture) than in the Netherlands (a low power distance culture); unlike in India, supervisors acted more like friends or equals with their subordinates in the Netherlands. Using vignettes, Study 2 found that, compared to informal support behaviours, formal support behaviours increased both affect- and cognition-based trust among Indian participants, but among US participants, …

Learning Transferable Negative Prompts For Out-Of-Distribution Detection, Tianqi Li, Guansong Pang, Xiao Bai, Wenjun Miao, Jin Zheng

Research Collection School Of Computing and Information Systems

Existing prompt learning methods have shown certain capabilities in Out-of-Distribution (OOD) detection, but the lack of OOD images in the target dataset in their training can lead to mismatches between OOD images and In-Distribution (ID) categories, resulting in a high false positive rate. To address this issue, we introduce a novel OOD detection method, named ‘NegPrompt’, to learn a set of negative prompts, each representing a negative connotation of a given class label, for delineating the boundaries between ID and OOD images. It learns such negative prompts with ID data only, without any reliance on external out-lier data. Further, current …

The Irreducible Otherness Of Desi And Desire In Singapore’S Gurdwaras: Moral Boundary-Making In The Shadows Of A Multicultural Society, Orlando Woods, Lily Kong

Research Collection College of Integrative Studies

This article considers the emergence of new multiculturalisms taking root in Asia by exploring how value-based frameworks and moral judgements are deployed to create new lines of difference within co-ethnic communities. These frameworks and judgements cause multiculturalism to become a more subjective, and thus splintered construct that is increasingly decoupled from state discourse. Further, it considers how religious spaces are typically associated with the performance of morally “right” attitudes and behaviours, and therefore provide fertile yet underexplored sites through which multicultural subjectivities are formed and enacted. It illustrates these theoretical ideas through an empirical examination of how moral boundary-making within …

Creating Synthetic Energy Meter Data Using Conditional Diffusion And Building Metadata, Chun Fu, Hussain Kazmi, Matias Quintana, Clayton Miller

Research Collection College of Integrative Studies

Advances in machine learning and increased computational power have driven progress in energy-related research. However, limited access to private energy data from buildings hinders traditional regression models relying on historical data. While generative models offer a solution, previous studies have primarily focused on short-term generation periods (e.g., daily profiles) and a limited number of meters. Thus, the study proposes a conditional diffusion model for generating high-quality synthetic energy data using relevant metadata. Using a dataset comprising 1,828 power meters from various buildings and countries, this model is compared with traditional methods like Conditional Generative Adversarial Networks (CGAN) and Conditional Variational …

Sgsh : Stimulate Large Language Models With Skeleton Heuristics For Knowledge Base Question Generation, Shasha Guo, Lizi Liao, Jing Zhang, Yanling Wang, Cuiping Li, Hong Chen

Research Collection School Of Computing and Information Systems

Knowledge base question generation (KBQG) aims to generate natural language questions from a set of triplet facts extracted from KB. Existing methods have significantly boosted the performance of KBQG via pre-trained language models (PLMs) thanks to the richly endowed semantic knowledge. With the advance of pre-training techniques, large language models (LLMs) (e.g., GPT-3.5) undoubtedly possess much more semantic knowledge. Therefore, how to effectively organize and exploit the abundant knowledge for KBQG becomes the focus of our study. In this work, we propose SGSH — a simple and effective framework to Stimulate GPT-3.5 with Skeleton Heuristics to enhance KBQG. The framework …

The Whole Is Better Than The Sum : Using Aggregated Demonstrations In In-Context Learning For Sequential Recommendation, Wang Lei, Ee-Peng Lim

Research Collection School Of Computing and Information Systems

Large language models (LLMs) have shown excellent performance on various NLP tasks. To use LLMs as strong sequential recommenders, we explore the in-context learning approach to sequential recommendation. We investigate the effects of instruction format, task consistency, demonstration selection, and number of demonstrations. As increasing the number of demonstrations in ICL does not improve accuracy despite using a long prompt, we propose a novel method called LLMSRec-Syn that incorporates multiple demonstration users into one aggregated demonstration. Our experiments on three recommendation datasets show that LLMSRec-Syn outperforms state-of-the-art LLM-based sequential recommendation methods. In some cases, LLMSRec-Syn can perform on par with …

Academic Search And Discovery Tools In The Age Of Ai And Large Language Models: An Overview Of The Space, Aaron Tay

2024 AI for Research Week

In the ever-evolving landscape of academic research, “AI tools” for literature search and synthesis are currently getting a lot of attention. These tools promise to ramp up productivity, enabling us to accomplish more in less time or absorb more knowledge without drowning in endless reading. With the sheer number of these systems increasing daily, it's natural to wonder: are they really worth our time and money? And if they are, how should we go about picking the right one from the multitude of options?

In this talk, I will share my views on how the space has developed over two …

Academic Literature Review In Age Of Ai And Large Language Models​, Aaron Tay

Research Collection Library

Explore the evolving landscape of academic research with a focus on open data and AI advancements, particularly in natural language processing. Join us for a practical presentation on leveraging emerging tools for literature review. Discover platforms like Connected Papers, ResearchRabbit, and Litmaps, offering paper exploration and recommendations based on initial 'seed papers.' Dive into AI-enhanced search engines like Elicit, Scispace, Semantic Scholar, and Scite.ai, powered by Large Language Models such as BERT and GPT. Learn about the latest developments, strengths, and weaknesses of these tools, and how they reshape literature review methods, from tool selection to query input techniques.

Unveiling Code Pre-Trained Models: Investigating Syntax And Semantics Capacities, Wei Ma, Shangqing Liu, Mengjie Zhao, Xiaofei Xie, Wenhang Wang, Qiang Hu, Jie Zhang, Liu Yang

Research Collection School Of Computing and Information Systems

Code models have made significant advancements in code intelligence by encoding knowledge about programming languages. While previous studies have explored the capabilities of these models in learning code syntax, there has been limited investigation on their ability to understand code semantics. Additionally, existing analyses assume the number of edges between nodes at the abstract syntax tree (AST) is related to syntax distance, and also often require transforming the high-dimensional space of deep learning models to a low-dimensional one, which may introduce inaccuracies. To study how code models represent code syntax and semantics, we conduct a comprehensive analysis of 7 code …

Enabling Roll-Up And Drill-Down Operations In News Exploration With Knowledge Graphs For Due Diligence And Risk Management, Sha Wang, Yuchen Li, Hanhua Xiao, Zhifeng Bao, Yanfei Dong

Research Collection School Of Computing and Information Systems

Efficient news exploration is crucial in real-world applications, particularly within the financial sector, where numerous control and risk assessment tasks rely on the analysis of public news reports. The current processes in this domain predominantly rely on manual efforts, often involving keyword-based searches and the compilation of extensive keyword lists. In this paper, we introduce NCEXPLORER, a framework designed with OLAP-like operations to enhance the news exploration experience. NCEXPLORER empowers users to use roll-up operations for a broader content overview and drill-down operations for detailed insights. These operations are achieved through integration with external knowledge graphs (KGs), encompassing both fact-based …

Enabling And Optimizing Multi-Modal Sense-Making For Human-Ai Interaction Tasks, Dulanga Kaveesha Weerakoon Weerakoon Mudiyanselage

Dissertations and Theses Collection (Open Access)

The rapid pace of adoption of mixed-reality in tandem with advances in NLP and computer vision have opened up unprecedented opportunities for more naturalistic interaction interfaces which underpin Human-AI collaborative applications such as spatial computing and interactive conversational agents. One notable example is the emergence of interactive virtual assistants, which facilitate more natural communication of instructions and queries through modalities like voice and text. This trend is driving the development of innovative ubiquitous, mixed-reality computing applications. Such interactive, natural communication is also critical to support advances in human-robot interactive co-working, across a variety of industrial, commercial and home environments. Conventional …

Towards Explainable Harmful Meme Detection Through Multimodal Debate Between Large Language Models, Hongzhan Lin, Ziyang Luo, Wei Gao, Jing Ma, Bo Wang, Ruichao Yang

Research Collection School Of Computing and Information Systems

The age of social media is flooded with Internet memes, necessitating a clear grasp and effective identification of harmful ones. This task presents a significant challenge due to the implicit meaning embedded in memes, which is not explicitly conveyed through the surface text and image. However, existing harmful meme detection methods do not present readable explanations that unveil such implicit meaning to support their detection decisions. In this paper, we propose an explainable approach to detect harmful memes, achieved through reasoning over conflicting rationales from both harmless and harmful positions. Specifically, inspired by the powerful capacity of Large Language Models …