Open Access. Powered by Scholars. Published by Universities.®
- Discipline
-
- Physical Sciences and Mathematics (1114)
- Computer Sciences (1105)
- Databases and Information Systems (529)
- Social and Behavioral Sciences (485)
- Artificial Intelligence and Robotics (354)
-
- Business (207)
- Software Engineering (190)
- International and Area Studies (184)
- Asian Studies (180)
- Graphics and Human Computer Interfaces (154)
- Numerical Analysis and Scientific Computing (149)
- Communication (130)
- Arts and Humanities (120)
- Programming Languages and Compilers (112)
- Law (101)
- Social Media (96)
- Psychology (81)
- Sociology (71)
- Education (68)
- Political Science (66)
- Engineering (63)
- Organizational Behavior and Theory (57)
- Philosophy (49)
- Computer Engineering (45)
- Public Affairs, Public Policy and Public Administration (35)
- Strategic Management Policy (33)
- Economics (31)
- Information Security (31)
- Higher Education (30)
- Theory and Algorithms (30)
- Keyword
-
- Social media (45)
- Singapore (38)
- Natural language processing (32)
- Deep learning (28)
- Machine learning (24)
-
- China (22)
- Large Language Models (20)
- Large language models (20)
- Culture (18)
- LLMs (18)
- Sentiment analysis (17)
- Text mining (16)
- Twitter (16)
- Software engineering (14)
- Generative AI (13)
- Indonesia (13)
- Language (13)
- Artificial intelligence (12)
- Neural networks (12)
- Computational linguistics (11)
- Creativity (10)
- Data mining (10)
- Large Language Model (10)
- Natural Language Processing (10)
- Performance (10)
- Bilingualism (9)
- Language model (9)
- Artificial Intelligence (8)
- Christianity (8)
- Deep Learning (8)
- Publication Year
- Publication
-
- Research Collection School Of Computing and Information Systems (1047)
- Research Collection School of Social Sciences (236)
- Research Collection Lee Kong Chian School Of Business (131)
- Research Collection Yong Pung How School Of Law (94)
- Dissertations and Theses Collection (Open Access) (58)
-
- Research Collection College of Integrative Studies (34)
- Research Collection School Of Accountancy (21)
- Research Collection School Of Economics (19)
- Asian Management Insights (6)
- Institute of Societal Leadership Research Collection (4)
- Perspectives@SMU (3)
- Research Collection Library (3)
- SCIS Student Publications (3)
- Student Publications (3)
- Centre for Computational Law (2022-2025) (2)
- Digital Narratives of Asia (2)
- FORCE 2026 (2)
- Knowledge@SMU (2)
- Social Space (2)
- 2008 Asian Business & Rule of Law initiative (1)
- 2012 AAPBS Academic Conference: Asian Business Leaders with a Global Mindset (1)
- 2012 Emerging Trends in Research Assessment Seminar (1)
- 2024 AI for Research Week (1)
- CCX Research (1)
- Dissertations and Theses Collection (1)
- Library Events (1)
- Lien Centre for Social Innovation: Research (1)
- Oral History Collection (1)
- PhD Student’s Publications Collection (1)
- Report to Stakeholders (1)
- Publication Type
- File Type
Articles 301 - 330 of 1690
Full-Text Articles in Entire DC Network
The Social Evaluation Of Accents And Perceived Social Influence In Singapore: A Comparison Of American And Singaporean English Accents, Matthew H. S. Ng, Chi-Ying Cheng
The Social Evaluation Of Accents And Perceived Social Influence In Singapore: A Comparison Of American And Singaporean English Accents, Matthew H. S. Ng, Chi-Ying Cheng
Research Collection School of Social Sciences
Accents are an important differentiator between groups which influence social perception and interaction, especially in a diverse country like Singapore. Social identity theory suggests that individuals would exhibit favoritism towards their own accents. However, the accent prestige theory demonstrates instances whereby foreign accents are perceived as more prestigious than one's own accent and are associated with more positive characteristics. This paper sought to explore which of these two theories is more prevalent in Singapore by comparing the perceptions of American English accents and local Singaporean English accents along the competence-warmth paradigm of the Stereotype Content Model. Further, the current research …
Text-Driven Video Prediction, Xue Song, Jingjing Chen, Bin Zhu, Yu-Gang Jiang
Text-Driven Video Prediction, Xue Song, Jingjing Chen, Bin Zhu, Yu-Gang Jiang
Research Collection School Of Computing and Information Systems
Current video generation models usually convert signals indicating appearance and motion received from inputs (e.g., image and text) or latent spaces (e.g., noise vectors) into consecutive frames, fulfilling a stochastic generation process for the uncertainty introduced by latent code sampling. However, this generation pattern lacks deterministic constraints for both appearance and motion, leading to uncontrollable and undesirable outcomes. To this end, we propose a new task called Text-driven Video Prediction (TVP). Taking the first frame and text caption as inputs, this task aims to synthesize the following frames. Specifically, appearance and motion components are provided by the image and caption …
Aligning Human And Computational Coherence Evaluations, Jia Peng Lim, Hady Wirawan Lauw
Aligning Human And Computational Coherence Evaluations, Jia Peng Lim, Hady Wirawan Lauw
Research Collection School Of Computing and Information Systems
Automated coherence metrics constitute an efficient and popular way to evaluate topic models. Previous work presents a mixed picture of their presumed correlation with human judgment. This work proposes a novel sampling approach to mining topic representations at a large scale while seeking to mitigate bias from sampling, enabling the investigation of widely used automated coherence metrics via large corpora. Additionally, this article proposes a novel user study design, an amalgamation of different proxy tasks, to derive a finer insight into the human decision-making processes. This design subsumes the purpose of simple rating and outlier-detection user studies. Similar to the …
Probing Effects Of Contextual Bias On Number Magnitude Estimation, Xuehao Du, Ping Ji, Wei Qin, Lei Wang, Yunshi Lan
Probing Effects Of Contextual Bias On Number Magnitude Estimation, Xuehao Du, Ping Ji, Wei Qin, Lei Wang, Yunshi Lan
Research Collection School Of Computing and Information Systems
The semantic understanding of numbers requires association with context. However, powerful neural networks overfit spurious correlations between context and numbers in training corpus can lead to the occurrence of contextual bias, which may affect the network's accurate estimation of number magnitude when making inferences in real-world data. To investigate the resilience of current methodologies against contextual bias, we introduce a novel out-of- distribution (OOD) numerical question-answering (QA) dataset that features specific correlations between context and numbers in the training data, which are not present in the OOD test data. We evaluate the robustness of different numerical encoding and decoding methods …
The Effect Of Nationalism On Governance Choices In Cross-Border Collaborations, Gokhan Ertug, Ilya R. P. Cuypers, Douglas Dow, Jesper Edman
The Effect Of Nationalism On Governance Choices In Cross-Border Collaborations, Gokhan Ertug, Ilya R. P. Cuypers, Douglas Dow, Jesper Edman
Research Collection Lee Kong Chian School Of Business
We examine how nationalism influences governance choice in cross-border collaborations. While nationalism has historically been within the purview of political scientists, we demonstrate its relevance to management scholars by theorizing how nationalist attitudes and behaviors among decision-makers might shape strategic decisions about collaborations with foreign partners. Drawing on insights from the social psychology literature, we theorize how two attitudes commonly associated with nationalism, i.e., lower levels of trust and an unwillingness to work with foreigners, may increase decision-makers’ concerns about opportunistic behavior and invasiveness in cross-border collaborations. Integrating these insights into two key theories of governance choice, i.e., transaction cost …
The Sacred Dimensions Of The Bri's Infrastructural Commons, Orlando Woods, David A. Palmer
The Sacred Dimensions Of The Bri's Infrastructural Commons, Orlando Woods, David A. Palmer
Research Collection College of Integrative Studies
Whilst the idea of infrastructure has animated scholarship for the past twenty years at least, there remains a need for more expansive understandings of what infrastructure is, and what it can be. The speed, scale and material disruptiveness with which many of the infrastructural megaprojects that constitute China’s Belt and Road Initiative (BRI) have been developed both underpin and validate this need. Whilst the effects of the BRI are both manifold and diffuse, all of them expose situations of infrastructural complexity. Rather than considering the BRI simply as the imposition of new material infrastructures on a landscape, we posit the …
Granular3d: Delving Into Multi-Granularity 3d Scene Graph Prediction, Kaixiang Huang, Jingru Yang, Jin Wang, Shengfeng He, Zhan Wang, Haiyan He, Qifeng Zhang, Guodong Lu
Granular3d: Delving Into Multi-Granularity 3d Scene Graph Prediction, Kaixiang Huang, Jingru Yang, Jin Wang, Shengfeng He, Zhan Wang, Haiyan He, Qifeng Zhang, Guodong Lu
Research Collection School Of Computing and Information Systems
This paper addresses the significant challenges in 3D Semantic Scene Graph (3DSSG) prediction, essential for understanding complex 3D environments. Traditional approaches, primarily using PointNet and Graph Convolutional Networks, struggle with effectively extracting multi-grained features from intricate 3D scenes, largely due to a focus on global scene processing and single-scale feature extraction. To overcome these limitations, we introduce Granular3D, a novel approach that shifts the focus towards multi-granularity analysis by predicting relation triplets from specific sub-scenes. One key is the Adaptive Instance Enveloping Method (AIEM), which establishes an approximate envelope structure around irregular instances, providing shape-adaptive local point cloud sampling, thereby …
Genixer : Empowering Multimodal Large Language Models As A Powerful Data Generator, Henry Hengyuan Zhao, Pan Zhou, Mike Zheng Shou
Genixer : Empowering Multimodal Large Language Models As A Powerful Data Generator, Henry Hengyuan Zhao, Pan Zhou, Mike Zheng Shou
Research Collection School Of Computing and Information Systems
Multimodal Large Language Models (MLLMs) demonstrate exceptional problem-solving capabilities, but few research studies aim to gauge the ability to generate visual instruction tuning data. This paper proposes to explore the potential of empowering MLLMs to generate data independently without relying on GPT-4. We introduce Genixer, a comprehensive data generation pipeline consisting of four key steps: (i) instruction data collection, (ii) instruction template design, (iii) empowering MLLMs, and (iv) data generation and filtering. Additionally, we outline two modes of data generation: task-agnostic and task-specific, enabling controllable output. We demonstrate that a synthetic VQA-like dataset trained with LLaVA1.5 enhances performance on 10 …
Enhancing Stance Classification On Social Media Using Quantified Moral Foundations, Hong Zhang, Quoc-Nam Nguyen, Prasanta Bhattacharya, Wei Gao, Liang Ze Wong, Brandon Siyuan Loh, Joseph J. P. Simons, Jisun An
Enhancing Stance Classification On Social Media Using Quantified Moral Foundations, Hong Zhang, Quoc-Nam Nguyen, Prasanta Bhattacharya, Wei Gao, Liang Ze Wong, Brandon Siyuan Loh, Joseph J. P. Simons, Jisun An
Research Collection School Of Computing and Information Systems
This study enhances stance detection on social media by incorporating deeper psychological attributes, specifically individuals’ moral foundations. These theoretically-derived dimensions aim to provide an interpretable profile of an individual’s moral concerns which, in recent work, has been linked to behaviour in a range of domains including society, politics, health, and the environment. In this paper, we investigate how moral foundation dimensions can contribute to detecting an individual’s stance on a given target. Specifically, we incorporate moral foundation features extracted from text, along with semantic features, to classify stances at both message-and user-levels using traditional machine learning and Large Language Models …
Chain-Of-Exemplar: Enhancing Distractor Generation For Multimodal Educational Question Generation, Haohao Luo, Yang Deng, Ying Shen, See-Kiong Ng, Tat-Seng Chua
Chain-Of-Exemplar: Enhancing Distractor Generation For Multimodal Educational Question Generation, Haohao Luo, Yang Deng, Ying Shen, See-Kiong Ng, Tat-Seng Chua
Research Collection School Of Computing and Information Systems
Multiple-choice questions (MCQs) are important in enhancing concept learning and student engagement for educational purposes. Despite the multimodal nature of educational content, current methods focus mainly on text-based inputs and often neglect the integration of visual information. In this work, we study the problem of multimodal educational question generation, which aims at generating subject-specific educational questions with plausible yet incorrect distractors based on multimodal educational content. To tackle this problem, we introduce a novel framework, named Chain-of-Exemplar (CoE), which utilizes multimodal large language models (MLLMs) with Chain-of-Thought reasoning to improve the generation of challenging distractors. Furthermore, CoE leverages three-stage contextualized …
Interpretable Tensor Fusion, Saurabh Varshneya, Antoine Ledent, Philipp Liznerski, Andriy Balinskyy, Purvanshi Mehta, Waleed Mustafa, Marius Kloft
Interpretable Tensor Fusion, Saurabh Varshneya, Antoine Ledent, Philipp Liznerski, Andriy Balinskyy, Purvanshi Mehta, Waleed Mustafa, Marius Kloft
Research Collection School Of Computing and Information Systems
Conventional machine learning methods are predominantly designed to predict outcomes based on a single data type. However, practical applications may encompass data of diverse types, such as text, images, and audio. We introduce interpretable tensor fusion (InTense), a multimodal learning method training a neural network to simultaneously learn multiple data representations and their interpretable fusion. InTense can separately capture both linear combinations and multiplicative interactions of the data types, thereby disentangling higher-order interactions from the individual effects of each modality. InTense provides interpretability out of the box by assigning relevance scores to modalities and their associations, respectively. The approach is …
Nonfactoid Question Answering As Query-Focused Summarization With Graph-Enhanced Multihop Inference, Yang Deng, Wenxuan Zhang, Weiwen Xu, Ying Shen, Wai Lam
Nonfactoid Question Answering As Query-Focused Summarization With Graph-Enhanced Multihop Inference, Yang Deng, Wenxuan Zhang, Weiwen Xu, Ying Shen, Wai Lam
Research Collection School Of Computing and Information Systems
Nonfactoid question answering (QA) is one of the most extensive yet challenging applications and research areas in natural language processing (NLP). Existing methods fall short of handling the long-distance and complex semantic relations between the question and the document sentences. In this work, we propose a novel query-focused summarization method, namely a graph-enhanced multihop query-focused summarizer (GMQS), to tackle the nonfactoid QA problem. Specifically, we leverage graph-enhanced reasoning techniques to elaborate the multihop inference process in nonfactoid QA. Three types of graphs with different semantic relations, namely semantic relevance, topical coherence, and coreference linking, are constructed for explicitly capturing the …
Style: Improving Domain Transferability Of Asking Clarification Questions In Large Language Model Powered Conversational Agents, Yue Chen, Chen Huang, Yang Deng, Wenqiang Lei, Dingnan Jin, Jia Liu, Tat-Seng Chua
Style: Improving Domain Transferability Of Asking Clarification Questions In Large Language Model Powered Conversational Agents, Yue Chen, Chen Huang, Yang Deng, Wenqiang Lei, Dingnan Jin, Jia Liu, Tat-Seng Chua
Research Collection School Of Computing and Information Systems
Equipping a conversational search engine with strategies regarding when to ask clarification questions is becoming increasingly important across various domains. Attributing to the context understanding capability of LLMs and their access to domain-specific sources of knowledge, LLM-based clarification strategies feature rapid transfer to various domains in a posthoc manner. However, they still struggle to deliver promising performance on unseen domains, struggling to achieve effective domain transferability. We take the first step to investigate this issue and existing methods tend to produce one-size-fits-all strategies across diverse domains, limiting their search effectiveness. In response, we introduce a novel method, called STYLE, to …
On The Multi-Turn Instruction Following For Conversational Web Agents, Yang Deng, Xuan Zhang, Wenxuan Zhang, Yifei Yuan, See-Kiong Ng, Tat-Seng Chua
On The Multi-Turn Instruction Following For Conversational Web Agents, Yang Deng, Xuan Zhang, Wenxuan Zhang, Yifei Yuan, See-Kiong Ng, Tat-Seng Chua
Research Collection School Of Computing and Information Systems
Web agents powered by Large Language Models (LLMs) have demonstrated remarkable abilities in planning and executing multi-step interactions within complex web-based environments, fulfilling a wide range of web navigation tasks. Despite these advancements, the potential for LLM-powered agents to effectively engage with sequential user instructions in real-world scenarios has not been fully explored. In this work, we introduce a new task of Conversational Web Navigation, which necessitates sophisticated interactions that span multiple turns with both the users and the environment, supported by a specially developed dataset named Multi-Turn Mind2Web (MT-Mind2Web). To tackle the limited context length of LLMs and the …
Watme: Towards Lossless Watermarking Through Lexical Redundancy, Liang Chen, Yatao Bian, Yang Deng, Deng Cai, Shuaiyi Li, Peilin Zhao, Kam-Fai Wong
Watme: Towards Lossless Watermarking Through Lexical Redundancy, Liang Chen, Yatao Bian, Yang Deng, Deng Cai, Shuaiyi Li, Peilin Zhao, Kam-Fai Wong
Research Collection School Of Computing and Information Systems
Text watermarking has emerged as a pivotal technique for identifying machine-generated text. However, existing methods often rely on arbitrary vocabulary partitioning during decoding to embed watermarks, which compromises the availability of suitable tokens and significantly degrades the quality of responses. This study assesses the impact of watermarking on different capabilities of large language models (LLMs) from a cognitive science lens. Our finding highlights a significant disparity; knowledge recall and logical reasoning are more adversely affected than language generation. These results suggest a more profound effect of watermarking on LLMs than previously understood. To address these challenges, we introduce Watermarking with …
Reinforcement Tuning For Detecting Stances And Debunking Rumors Jointly With Large Language Models, Ruichao Yang, Wei Gao, Jing Ma, Hongzhan Ling, Bo Wang
Reinforcement Tuning For Detecting Stances And Debunking Rumors Jointly With Large Language Models, Ruichao Yang, Wei Gao, Jing Ma, Hongzhan Ling, Bo Wang
Research Collection School Of Computing and Information Systems
Learning multi-task models for jointly detecting stance and verifying rumors poses challenges due to the need for training data of stance at post level and rumor veracity at claim level, which are difficult to obtain. To address this issue, we leverage large language models (LLMs) as the foundation annotators for the joint stance detection (SD) and rumor verification (RV) tasks, dubbed as JSDRV. We introduce a novel reinforcement tuning framework to enhance the joint predictive capabilities of LLM-based SD and RV components. Specifically, we devise a policy for selecting LLM-annotated data at the two levels, employing a hybrid reward mechanism …
Empathyear : An Open-Source Avatar Multimodal Empathetic Chatbot, Hao Fei, Han Zhang, Bin Wang, Lizi Liao, Qian Liu, Erik Cambria
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 …
Analyzing Temporal Complex Events With Large Language Models? A Benchmark Towards Temporal, Long Context Understanding, Zhihan Zhang, Yixin Cao, Chenchen Ye, Ma. Yunshan, Lizi Liao, Tat-Seng Chua
Analyzing Temporal Complex Events With Large Language Models? A Benchmark Towards Temporal, Long Context Understanding, Zhihan Zhang, Yixin Cao, Chenchen Ye, Ma. Yunshan, Lizi Liao, Tat-Seng Chua
Research Collection School Of Computing and Information Systems
The digital landscape is rapidly evolving with an ever-increasing volume of online news, emphasizing the need for swift and precise analysis of complex events.We refer to the complex events composed of many news articles over an extended period as Temporal Complex Event (TCE). This paper proposes a novel approach using Large Language Models (LLMs) to systematically extract and analyze the event chain within TCE, characterized by their key points and timestamps. We establish a benchmark, named TCELongBench, to evaluate the proficiency of LLMs in handling temporal dynamics and understanding extensive text. This benchmark encompasses three distinct tasks - reading comprehension, …
A Theory Of Host Country Sentiments: An Illustration In Cross-Border Acquisitions, Daphne W. Yiu, William P. Wan, Xiaocong Tian, Kelly Xing Chen
A Theory Of Host Country Sentiments: An Illustration In Cross-Border Acquisitions, Daphne W. Yiu, William P. Wan, Xiaocong Tian, Kelly Xing Chen
Research Collection Lee Kong Chian School Of Business
Capitalizing on massive sentiment diffusion and mobilization aided by mass media and social media nowadays, we introduce a general theory of host country sentiments to illuminate the granular, context-situated, and time dynamic power of social sentiments. We posit that host country is a value-laden context wherein a foreign entity’s strategic action stimulates host country stakeholders’ social sentiments and engagement in systems of discourses (“sentiment arousal”), mobilizes social sentiments toward the foreign entity (“sentiment competence”), and legitimizes social sentiments and the strategic action of the foreign entity (“sentiment resonance”). To test our theory, we employ a context of inward acquisitions by …
Ten Years As Boundary Object: The Search For Identity And Belonging As 'Hongkongers', John Lowe, Darlene Machell Espena, George Wong
Ten Years As Boundary Object: The Search For Identity And Belonging As 'Hongkongers', John Lowe, Darlene Machell Espena, George Wong
Research Collection College of Integrative Studies
This article examines the complex process of symbolic boundary-making of ‘Hongkonger’ cultural identities through the lens of the controversial 2015 film Ten Years, which is a celebrated omnibus production comprised of five short segments that picture a dystopic end to Hong Kong’s cherished way of life in the year 2025. The article is premised on an interdisciplinary approach engaging with cultural studies and film studies. On one hand, it explores how Ten Years functioned as a boundary object, a vast terrain within which cultural identities of what it means to be a Hongkonger are constructed, banished, imagined, and performed under …
Ee-Lce: An Event Extraction Framework Based On Llm-Generated Cot Explanation, Yanhua Yu, Yuanlong Wang, Yunshan Ma, Jie Li, Kangkang Lu, Zhiyong Huang, Tat-Seng Chua
Ee-Lce: An Event Extraction Framework Based On Llm-Generated Cot Explanation, Yanhua Yu, Yuanlong Wang, Yunshan Ma, Jie Li, Kangkang Lu, Zhiyong Huang, Tat-Seng Chua
Research Collection School Of Computing and Information Systems
Generative models have been widely used in event extraction. However, the interpretability of event extraction has not been fully investigated. In this paper, we propose an Event Extraction framework based on LLM-generated CoT Explanation EE-LCE, which can generate chain-of-thought-style (CoT-style) explanations for events. To this end, we provide each sample of event datasets with an explanation of the reasoning process using a large language model (LLM) GPT-3.5, and fine-tune the Flan-T5 lightweight language model (LM) supervised by the augmented dataset, enhancing both interpretability and performance of the event extraction. Moreover, we use a prefix tree (trie) to normalize the decoding …
Larp: Language Audio Relational Pre‑Training For Cold‑Start Playlist Continuation, Rebecca Salganik, Xiaohao Liu, Yunshan Ma, Jian Kang, Tat‑Seng Chua
Larp: Language Audio Relational Pre‑Training For Cold‑Start Playlist Continuation, Rebecca Salganik, Xiaohao Liu, Yunshan Ma, Jian Kang, Tat‑Seng Chua
Research Collection School Of Computing and Information Systems
As online music consumption increasingly shifts towards playlist-based listening, the task of playlist continuation, in which an algorithm suggests songs to extend a playlist in a personalized and musically cohesive manner, has become vital to the success of music streaming services. Currently, many existing playlist continuation approaches rely on collaborative filtering methods to perform their recommendations. However, such methods will struggle to recommend songs that lack interaction data, an issue known as the cold-start problem. Current approaches to this challenge design complex mechanisms for extracting relational signals from sparse collaborative signals and integrating them into content representations. However, these approaches …
Self-Chats From Large Language Models Make Small Emotional Support Chatbot Better, Zhonghua Zheng, Lizi Liao, Yang Deng, Libo Qin, Liqiang Nie
Self-Chats From Large Language Models Make Small Emotional Support Chatbot Better, Zhonghua Zheng, Lizi Liao, Yang Deng, Libo Qin, Liqiang Nie
Research Collection School Of Computing and Information Systems
Large Language Models (LLMs) have shown strong generalization abilities to excel in various tasks, including emotion support conversations. However, deploying such LLMs like GPT-3 (175B parameters) is resource-intensive and challenging at scale. In this study, we utilize LLMs as “Counseling Teacher” to enhance smaller models’ emotion support response abilities, significantly reducing the necessity of scaling up model size. To this end, we first introduce an iterative expansion framework, aiming to prompt the large teacher model to curate an expansive emotion support dialogue dataset. This curated dataset, termed ExTES, encompasses a broad spectrum of scenarios and is crafted with meticulous strategies …
Planning Like Human : A Dual-Process Framework For Dialogue Planning, Tao He, Lizi Liao, Yixin Cao, Yuanxing Liu, Ming Liu, Zerui Chen, Bing Qin
Planning Like Human : A Dual-Process Framework For Dialogue Planning, Tao He, Lizi Liao, Yixin Cao, Yuanxing Liu, Ming Liu, Zerui Chen, Bing Qin
Research Collection School Of Computing and Information Systems
In proactive dialogue, the challenge lies not just in generating responses but in steering conversations toward predetermined goals, a task where Large Language Models (LLMs) typically struggle due to their reactive nature. Traditional approaches to enhance dialogue planning in LLMs, ranging from elaborate prompt engineering to the integration of policy networks, either face efficiency issues or deliver suboptimal performance. Inspired by the dual-process theory in psychology, which identifies two distinct modes of thinking—intuitive (fast) and analytical (slow), we propose the Dual-Process Dialogue Planning (DPDP) framework. DPDP embodies this theory through two complementary planning systems: an instinctive policy model for familiar …
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
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 …
Sibo : A Simple Booster For Parameter-Efficient Fine-Tuning, Zhihao Wen, Jie Zhang, Yuan Fang
Sibo : A Simple Booster For Parameter-Efficient Fine-Tuning, Zhihao Wen, Jie Zhang, Yuan Fang
Research Collection School Of Computing and Information Systems
Fine-tuning all parameters of large language models (LLMs) necessitates substantial computational power and extended time. Latest advancements in parameter-efficient fine-tuning (PEFT) techniques, such as Adapter tuning and LoRA, allow for adjustments to only a minor fraction of the parameters of these LLMs. Concurrently, it has been noted that the issue of over-smoothing diminishes the effectiveness of these Transformer-based LLMs, resulting in suboptimal performances in downstream tasks. In this paper, we present SIBO, which is a SImple BOoster to enhance PEFT, by injecting an initial residual. SIBO is straightforward and readily extensible to a range of state-of-the-art PEFT techniques to alleviate …
Heterogeneous Graph Transformer With Poly-Tokenization, Zhiyuan Lu, Yuan Fang, Cheng Yang, Chuan Shi
Heterogeneous Graph Transformer With Poly-Tokenization, Zhiyuan Lu, Yuan Fang, Cheng Yang, Chuan Shi
Research Collection School Of Computing and Information Systems
Graph neural networks have shown widespread success for learning on graphs, but they still face fundamental drawbacks, such as limited expressive power, over-smoothing, and over-squashing. Meanwhile, the transformer architecture offers a potential solution to these issues. However, existing graph transformers primarily cater to homogeneous graphs and are unable to model the intricate semantics of heterogeneous graphs. Moreover, unlike small molecular graphs where the entire graph can be considered as the receptive field in graph transformers, real-world heterogeneous graphs comprise a significantly larger number of nodes and cannot be entirely treated as such. Consequently, existing graph transformers struggle to capture the …
Synergizing Large Language Models And Pre-Trained Smaller Models For Conversational Intent Discovery, Jinggui Liang, Lizi Liao, Hao Fei, Jing Jiang
Synergizing Large Language Models And Pre-Trained Smaller Models For Conversational Intent Discovery, Jinggui Liang, Lizi Liao, Hao Fei, Jing Jiang
Research Collection School Of Computing and Information Systems
In Conversational Intent Discovery (CID), Small Language Models (SLMs) struggle with overfitting to familiar intents and fail to label newly discovered ones. This issue stems from their limited grasp of semantic nuances and their intrinsically discriminative framework. Therefore, we propose Synergizing Large Language Models (LLMs) with pre-trained SLMs for CID (SynCID). It harnesses the profound semantic comprehension of LLMs alongside the operational agility of SLMs. By utilizing LLMs to refine both utterances and existing intent labels, SynCID significantly enhances the semantic depth, subsequently realigning these enriched descriptors within the SLMs’ feature space to correct cluster distortion and promote robust learning …
A Survey On Neural Question Generation : Methods, Applications, And Prospects, Shasha Guo, Lizi Liao, Cuiping Li, Tat-Seng Chua
A Survey On Neural Question Generation : Methods, Applications, And Prospects, Shasha Guo, Lizi Liao, Cuiping Li, Tat-Seng Chua
Research Collection School Of Computing and Information Systems
In this survey, we present a detailed examination of the advancements in Neural Question Generation (NQG), a field leveraging neural network techniques to generate relevant questions from diverse inputs like knowledge bases, texts, and images. The survey begins with an overview of NQG’s background, encompassing the task’s problem formulation, prevalent benchmark datasets, established evaluation metrics, and notable applications. It then methodically classifies NQG approaches into three predominant categories: structured NQG, which utilizes organized data sources, unstructured NQG, focusing on more loosely structured inputs like texts or visual content, and hybrid NQG, drawing on diverse input modalities. This classification is followed …
Speaker Verification In Agent-Generated Conversations, Yizhe Yang, Palakorn Achananuparp, Heyan Huang, Jing Jiang, Ee-Peng Lim
Speaker Verification In Agent-Generated Conversations, Yizhe Yang, Palakorn Achananuparp, Heyan Huang, Jing Jiang, Ee-Peng Lim
Research Collection School Of Computing and Information Systems
The recent success of large language models (LLMs) has attracted widespread interest to develop role-playing conversational agents personalized to the characteristics and styles of different speakers to enhance their abilities to perform both general and special purpose dialogue tasks. However, the ability to personalize the generated utterances to speakers, whether conducted by human or LLM, has not been well studied. To bridge this gap, our study introduces a novel evaluation challenge: speaker verification in agent-generated conversations, which aimed to verify whether two sets of utterances originate from the same speaker. To this end, we assemble a large dataset collection encompassing …