Open Access. Powered by Scholars. Published by Universities.®

Databases and Information Systems Commons™

Open Access. Powered by Scholars. Published by Universities.®

Discipline
Institution
Keyword
Publication Year
Publication
Publication Type
File Type

Articles 61 - 90 of 6572

Full-Text Articles in Databases and Information Systems

Unmasking Shadows: Unraveling Crime Patterns In Nyc's Boroughs, Jack Hachicho, Muhammad Hassan Butt Dec 2023

Unmasking Shadows: Unraveling Crime Patterns In Nyc's Boroughs, Jack Hachicho, Muhammad Hassan Butt

Publications and Research

New York City's crime dynamics have been on the rise for decades. Brooklyn and The Bronx have been disproportionately affected. This research aims to understand the crime landscape in these boroughs to formulate effective policies. Using crime data from official sources, statistical analyses, and data visualizations, the study identifies patterns and trends. The data encompasses over 400,000 reported incidents collected over the past 10 years, meticulously categorized by borough, crime type, and demographic information. Brooklyn has the highest overall crime rate, followed by The Bronx. Most shooting victims are Black. This highlights the need for holistic community programs to address …

Go to article

Les Expositions Turnus, Une Page D’Histoire Transnationale Des Beaux-Arts En Suisse À La Fin Du Xixe Siècle. Et Comment Découvrir Les Humanités Numériques, Béatrice Joyeux-Prunel Dec 2023

Les Expositions Turnus, Une Page D’Histoire Transnationale Des Beaux-Arts En Suisse À La Fin Du Xixe Siècle. Et Comment Découvrir Les Humanités Numériques, Béatrice Joyeux-Prunel

Artl@s Bulletin

Cet article présente le travail de la classe d’introduction aux humanités numériques de l’Université de Genève sur les expositions Turnus en Suisse à partir des années 1840. Près de 50 catalogues ont été retranscrits, décrits et structurés à l’aide de scripts Python, puis géolocalisés. Les données ont été ajoutées à BasArt, le répertoire mondial de catalogues d’expositions d’Artl@s (https://artlas.huma-num.fr/map). Elles permettent de mieux comprendre les premières années de ces expositions et leurs dynamiques locales, fédérales et internationales. Le Turnus fut une plaque tournante pour les artistes suisses, voire un tremplin vers le marché européen de l’art.

Go to article

Index Bucketing: A Novel Approach To Manipulating Data Structures, Jeffrey Myers Dec 2023

Index Bucketing: A Novel Approach To Manipulating Data Structures, Jeffrey Myers

Masters Theses & Specialist Projects

Handling nested data collections in large-scale distributed systems poses considerable challenges in query processing, often resulting in substantial costs and error susceptibility. While substantial efforts have been directed toward overcoming computation hurdles in querying vast data collections within relational databases, scant attention has been devoted to the manipulation and flattening procedures necessary for unnesting these data collections. Flattening operations, integral to unnesting, frequently yield copious duplicate data and entail a loss of information, devoid of mechanisms for reconstructing the original structure. These challenges exacerbate in scenarios involving skewed, nested data with irregular inner data collections. Processing such data demands an …

Go to article

Big Data Applications And Challenges In Giscience (Case Studies: Natural Disaster And Public Health Crisis Management), Amir Masoud Forati Dec 2023

Big Data Applications And Challenges In Giscience (Case Studies: Natural Disaster And Public Health Crisis Management), Amir Masoud Forati

Theses and Dissertations

This dissertation examines the application and significance of user-generated big data in Geographic Information Science (GIScience), with a focus on managing natural disasters and public health crises. It explores the role of social media data in understanding human-environment interactions and in informing disaster management and public health strategies. A scalable computational framework will be developed to model extensive unstructured geotagged data from social media, facilitating systematic spatiotemporal data analysis.The research investigates how individuals and communities respond to high-impact events like natural disasters and public health emergencies, employing both qualitative and quantitative methods. In particular, it assesses the impact of socio-economic-demographic …

Go to article

Self-Supervised Pseudo Multi-Class Pre-Training For Unsupervised Anomaly Detection And Segmentation In Medical Images, Yu Tian, Fengbei Liu, Guansong Pang, Yuanhong Chen, Yuyuan Liu, Johan W. Verjans, Rajvinder Singh, Gustavo Carneiro Dec 2023

Self-Supervised Pseudo Multi-Class Pre-Training For Unsupervised Anomaly Detection And Segmentation In Medical Images, Yu Tian, Fengbei Liu, Guansong Pang, Yuanhong Chen, Yuyuan Liu, Johan W. Verjans, Rajvinder Singh, Gustavo Carneiro

Research Collection School Of Computing and Information Systems

Unsupervised anomaly detection (UAD) methods are trained with normal (or healthy) images only, but during testing, they are able to classify normal and abnormal (or disease) images. UAD is an important medical image analysis (MIA) method to be applied in disease screening problems because the training sets available for those problems usually contain only normal images. However, the exclusive reliance on normal images may result in the learning of ineffective low-dimensional image representations that are not sensitive enough to detect and segment unseen abnormal lesions of varying size, appearance, and shape. Pre-training UAD methods with self-supervised learning, based on computer …

Go to article

Combat Covid-19 At National Level Using Risk Stratification With Appropriate Intervention, Xuan Jin, Kar Way Tan Dec 2023

Combat Covid-19 At National Level Using Risk Stratification With Appropriate Intervention, Xuan Jin, Kar Way Tan

Research Collection School Of Computing and Information Systems

In the national battle against COVID-19, harnessing population-level big data is imperative, enabling authorities to devise effective care policies, allocate healthcare resources efficiently, and enact targeted interventions. Singapore adopted the Home Recovery Programme (HRP) in September 2021, diverting low-risk COVID-19 patients to home care to ease hospital burdens amid high vaccination rates and mild symptoms. While a patient's suitability for HRP could be assessed using broad-based criteria, integrating machine learning (ML) model becomes invaluable for identifying high-risk patients prone to severe illness, facilitating early medical assessment. Most prior studies have traditionally depended on clinical and laboratory data, necessitating initial clinic …

Go to article

Data-Centric Image Super-Resolution In Magnetic Resonance Imaging: Challenges And Opportunities, Mamata Shrestha Dec 2023

Data-Centric Image Super-Resolution In Magnetic Resonance Imaging: Challenges And Opportunities, Mamata Shrestha

Graduate Theses and Dissertations

Super-resolution has emerged as a crucial research topic in the field of Magnetic Resonance Imaging (MRI) where it plays an important role in understanding and analysis of complex, qualitative, and quantitative characteristics of tissues at high resolutions. Deep learning techniques have been successful in achieving state-of-the-art results for super-resolution. These deep learning-based methods heavily rely on a substantial amount of data. Additionally, they require a pair of low-resolution and high-resolution images for supervised training which is often unavailable. Particularly in MRI super-resolution, it is often impossible to have low-resolution and high-resolution training image pairs. To overcome this, existing methods for …

Go to article

Mermaid: A Dataset And Framework For Multimodal Meme Semantic Understanding, Shaun Toh, Adriel Kuek, Wen Haw Chong, Roy Ka Wei Lee Dec 2023

Mermaid: A Dataset And Framework For Multimodal Meme Semantic Understanding, Shaun Toh, Adriel Kuek, Wen Haw Chong, Roy Ka Wei Lee

Research Collection School Of Computing and Information Systems

Memes are widely used to convey cultural and societal issues and have a significant impact on public opinion. However, little work has been done on understanding and explaining the semantics expressed in multimodal memes. To fill this research gap, we introduce MERMAID, a dataset consisting of 3,633 memes annotated with their entities and relations, and propose a novel MERF pipeline that extracts entities and their relationships in memes. Our framework combines state-of-the-art techniques from natural language processing and computer vision to extract text and image features and infer relationships between entities in memes. We evaluate the proposed framework on a …

Go to article

Flowpg: Action-Constrained Policy Gradient With Normalizing Flows, Brahmanage Janaka Chathuranga Thilakarathna, Jiajing Ling, Akshat Kumar Dec 2023

Flowpg: Action-Constrained Policy Gradient With Normalizing Flows, Brahmanage Janaka Chathuranga Thilakarathna, Jiajing Ling, Akshat Kumar

Research Collection School Of Computing and Information Systems

Action-constrained reinforcement learning (ACRL) is a popular approach for solving safety-critical and resource-allocation related decision making problems. A major challenge in ACRL is to ensure agent taking a valid action satisfying constraints in each RL step. Commonly used approach of using a projection layer on top of the policy network requires solving an optimization program which can result in longer training time, slow convergence, and zero gradient problem. To address this, first we use a normalizing flow model to learn an invertible, differentiable mapping between the feasible action space and the support of a simple distribution on a latent variable, …

Go to article

C³: Code Clone-Based Identification Of Duplicated Components, Yanming Yang, Ying Zou, Xing Hu, David Lo, Chao Ni, John C. Grundy, Xin: Xia Dec 2023

C³: Code Clone-Based Identification Of Duplicated Components, Yanming Yang, Ying Zou, Xing Hu, David Lo, Chao Ni, John C. Grundy, Xin: Xia

Research Collection School Of Computing and Information Systems

Reinventing the wheel is a detrimental programming practice in software development that frequently results in the introduction of duplicated components. This practice not only leads to increased maintenance and labor costs but also poses a higher risk of propagating bugs throughout the system. Despite numerous issues introduced by duplicated components in software, the identification of component-level clones remains a significant challenge that existing studies struggle to effectively tackle. Specifically, existing methods face two primary limitations that are challenging to overcome: 1) Measuring the similarity between different components presents a challenge due to the significant size differences among them; 2) Identifying …

Go to article

Extending The Horizon By Empowering Government Customer Service Officers With Acqar For Enhanced Citizen Service Delivery, Hui Shan Lee, Shankararaman, Venky, Eng Lieh Ouh Dec 2023

Extending The Horizon By Empowering Government Customer Service Officers With Acqar For Enhanced Citizen Service Delivery, Hui Shan Lee, Shankararaman, Venky, Eng Lieh Ouh

Research Collection School Of Computing and Information Systems

A previous study on the use of the Empath library in the prediction of Service Level Agreements (SLA) reveals the quality levels required for meaningful interaction between government customer service officers and citizens. On the other hand, past implementation of the Citizen Question-Answer system (CQAS), a type of Question-Answer model, suggests that such models if put in place can empower government customer service officers to reply faster and better with recommended answers. This study builds upon the research outcomes from both arenas of studies and introduces an innovative system design that allows the officers to incorporate the outputs from Empath …

Go to article

Llm-Adapters: An Adapter Family For Parameter-Efficient Fine-Tuning Of Large Language Models, Zhiqiang Hu, Lei Wang, Yihuai Lan, Wanyu Xu, Ee-Peng Lim, Lidong Bing, Xing Xu, Soujanya Poria, Roy Ka-Wei Lee Dec 2023

Llm-Adapters: An Adapter Family For Parameter-Efficient Fine-Tuning Of Large Language Models, Zhiqiang Hu, Lei Wang, Yihuai Lan, Wanyu Xu, Ee-Peng Lim, Lidong Bing, Xing Xu, Soujanya Poria, Roy Ka-Wei Lee

Research Collection School Of Computing and Information Systems

The success of large language models (LLMs), like GPT-4 and ChatGPT, has led to the development of numerous cost-effective and accessible alternatives that are created by finetuning open-access LLMs with task-specific data (e.g., ChatDoctor) or instruction data (e.g., Alpaca). Among the various fine-tuning methods, adapter-based parameter-efficient fine-tuning (PEFT) is undoubtedly one of the most attractive topics, as it only requires fine-tuning a few external parameters instead of the entire LLMs while achieving comparable or even better performance. To enable further research on PEFT methods of LLMs, this paper presents LLMAdapters, an easy-to-use framework that integrates various adapters into LLMs and …

Go to article

A Review Of Threat Vectors To Dna Sequencing Pipelines, Tyler Rector Dec 2023

A Review Of Threat Vectors To Dna Sequencing Pipelines, Tyler Rector

Cybersecurity Undergraduate Research Showcase

Bioinformatics is a steadily growing field that focuses on the intersection of biology with computer science. Tools and techniques developed within this field are quickly becoming fixtures in genomics, forensics, epidemiology, and bioengineering. The development and analysis of DNA sequencing and synthesis have enabled this significant rise in demand for bioinformatic tools. Notwithstanding, these bioinformatic tools have developed in a research context free of significant cybersecurity threats. With the significant growth of the field and the commercialization of genetic information, this is no longer the case. This paper examines the bioinformatic landscape through reviewing the biological and cybersecurity threats within …

Go to article

Damage Detection With An Integrated Smart Composite Using A Magnetostriction-Based Nondestructive Evaluation Method: Integrating Machine Learning For Prediction, Christopher Nelon Dec 2023

Damage Detection With An Integrated Smart Composite Using A Magnetostriction-Based Nondestructive Evaluation Method: Integrating Machine Learning For Prediction, Christopher Nelon

All Dissertations

The development of composite materials for structural components necessitates methods for evaluating and characterizing their damage states after encountering loading conditions. Laminates fabricated from carbon fiber reinforced polymers (CFRPs) are lightweight alternatives to metallic plates; thus, their usage has increased in performance industries such as aerospace and automotive. Additive manufacturing (AM) has experienced a similar growth as composite material inclusion because of its advantages over traditional manufacturing methods. Fabrication with composite laminates and additive manufacturing, specifically fused filament fabrication (fused deposition modeling), requires material to be placed layer-by-layer. If adjacent plies/layers lose adhesion during fabrication or operational usage, the strength …

Go to article

Ensemble-Based Deep Reinforcement Learning For Vehicle Routing Problems Under Distribution Shift, Yuan Jiang, Zhiguang Cao, Yaoxin Wu, Wen Song, Jie Zhang Dec 2023

Ensemble-Based Deep Reinforcement Learning For Vehicle Routing Problems Under Distribution Shift, Yuan Jiang, Zhiguang Cao, Yaoxin Wu, Wen Song, Jie Zhang

Research Collection School Of Computing and Information Systems

While performing favourably on the independent and identically distributed (i.i.d.) instances, most of the existing neural methods for vehicle routing problems (VRPs) struggle to generalize in the presence of a distribution shift. To tackle this issue, we propose an ensemble-based deep reinforcement learning method for VRPs, which learns a group of diverse sub-policies to cope with various instance distributions. In particular, to prevent convergence of the parameters to the same one, we enforce diversity across sub-policies by leveraging Bootstrap with random initialization. Moreover, we also explicitly pursue inequality between sub-policies by exploiting regularization terms during training to further enhance diversity. …

Go to article

Monocular Depth Estimation For Glass Walls With Context: A New Dataset And Method, Yuan Liang, Bailin Deng, Wenxi Liu, Jing Qin, Shengfeng He Dec 2023

Monocular Depth Estimation For Glass Walls With Context: A New Dataset And Method, Yuan Liang, Bailin Deng, Wenxi Liu, Jing Qin, Shengfeng He

Research Collection School Of Computing and Information Systems

Traditional monocular depth estimation assumes that all objects are reliably visible in the RGB color domain. However, this is not always the case as more and more buildings are decorated with transparent glass walls. This problem has not been explored due to the difficulties in annotating the depth levels of glass walls, as commercial depth sensors cannot provide correct feedbacks on transparent objects. Furthermore, estimating depths from transparent glass walls requires the aids of surrounding context, which has not been considered in prior works. To cope with this problem, we introduce the first Glass Walls Depth Dataset (GW-Depth dataset). We …

Go to article

Spatial-Temporal Episodic Memory Modeling For Adls: Encoding, Retrieval, And Prediction, Xinjing Song, Di Wang, Chai Quek, Ah-Hwee Tan, Yanjiang Wang Dec 2023

Spatial-Temporal Episodic Memory Modeling For Adls: Encoding, Retrieval, And Prediction, Xinjing Song, Di Wang, Chai Quek, Ah-Hwee Tan, Yanjiang Wang

Research Collection School Of Computing and Information Systems

Activities of daily living (ADLs) relate to people’s daily self-care activities, which reflect their living habits and lifestyle. A prior study presented a neural network model called STADLART for ADL routine learning. In this paper, we propose a cognitive model named Spatial-Temporal Episodic Memory for ADL (STEM-ADL), which extends STADLART to encode event sequences in the form of distributed episodic memory patterns. Specifically, STEM-ADL encodes each ADL and its associated contextual information as an event pattern and encodes all events in a day as an episode pattern. By explicitly encoding the temporal characteristics of events as activity gradient patterns, STEM-ADL …

Go to article

On The Usage Of Continual Learning For Out-Of-Distribution Generalization In Pre-Trained Language Models Of Code, Martin Weyssow, Xin Zhou, Kisub Kim, David Lo, Houari A. Sahraoui Dec 2023

On The Usage Of Continual Learning For Out-Of-Distribution Generalization In Pre-Trained Language Models Of Code, Martin Weyssow, Xin Zhou, Kisub Kim, David Lo, Houari A. Sahraoui

Research Collection School Of Computing and Information Systems

Pre-trained language models (PLMs) have become a prevalent technique in deep learning for code, utilizing a two-stage pre-training and fine-tuning procedure to acquire general knowledge about code and specialize in a variety of downstream tasks. However, the dynamic nature of software codebases poses a challenge to the effectiveness and robustness of PLMs. In particular, world-realistic scenarios potentially lead to significant differences between the distribution of the pre-training and test data, i.e., distribution shift, resulting in a degradation of the PLM's performance on downstream tasks. In this paper, we stress the need for adapting PLMs of code to software data whose …

Go to article

Reinforced Target-Driven Conversational Promotion, Huy Quang Dao, Lizi Liao, Dung D. Le, Yuxiang Nie Dec 2023

Reinforced Target-Driven Conversational Promotion, Huy Quang Dao, Lizi Liao, Dung D. Le, Yuxiang Nie

Research Collection School Of Computing and Information Systems

The ability to proactively engage with users towards pitching products is highly desired for conversational assistants. However, existing conversational recommendation methods overemphasize on acquiring user preferences while ignore the strategic planning for nudging users towards accepting a designated item. Hence, these methods fail to promote specified items with engaging responses. In this work, we propose a Reinforced Target-driven Conversational Promotion (RTCP) framework for conversational promotion. RTCP integrates short-term and long-term planning via a balanced gating mechanism. Inside which, the dialogue actions are predicted via a knowledge-integrated multi-head attention and guided via reinforcement learning rewards. RTCP then employs action-guided prefix tuning …

Go to article

Making Data Meaningful: Stakeholder Perceptions On Data Visualization And Data Management Practices Within A Multi-Tiered System Of Supports (Mtss), Domenick Saia Dec 2023

Making Data Meaningful: Stakeholder Perceptions On Data Visualization And Data Management Practices Within A Multi-Tiered System Of Supports (Mtss), Domenick Saia

Dissertations

Data-driven decision-making and collaboration are core pillars of a multi-tiered system of supports (MTSS); however, timely and accessible data use, as well as data literacy and visualization literacy skills, are challenges school leaders and educators face related to implementing such frameworks. I hypothesized efficient data management systems and data visualization tools enable school teams to predict student learning outcomes, readily communicate, and better understand student data. The purpose of this study design was to highlight a need for more efficient data structures that allow school stakeholders to balance their roles within an MTSS framework more effectively. The context of this …

Go to article

The Value Of Official Website Information In The Credit Risk Evaluation Of Smes, Cuiqing Jiang, Chang Yin, Qian Tang, Zhao Wang Dec 2023

The Value Of Official Website Information In The Credit Risk Evaluation Of Smes, Cuiqing Jiang, Chang Yin, Qian Tang, Zhao Wang

Research Collection School Of Computing and Information Systems

The official websites of small and medium-sized enterprises (SMEs) not only reflect the willingness of an enterprise to disclose information voluntarily, but also can provide information related to the enterprises’ historical operations and performance. This research investigates the value of official website information in the credit risk evaluation of SMEs. To study the effect of different kinds of website information on credit risk evaluation, we propose a framework to mine effective features from two kinds of information disclosed on the official website of a SME—design-based information and content-based information—in predicting its credit risk. We select the SMEs in the software …

Go to article

Llm4vis: Explainable Visualization Recommendation Using Chatgpt, Lei Wang, Songheng Zhang, Yun Wang, Ee-Peng Lim, Yong Wang Dec 2023

Llm4vis: Explainable Visualization Recommendation Using Chatgpt, Lei Wang, Songheng Zhang, Yun Wang, Ee-Peng Lim, Yong Wang

Research Collection School Of Computing and Information Systems

Data visualization is a powerful tool for exploring and communicating insights in various domains. To automate visualization choice for datasets, a task known as visualization recommendation has been proposed. Various machine-learning-based approaches have been developed for this purpose, but they often require a large corpus of dataset-visualization pairs for training and lack natural explanations for their results. To address this research gap, we propose LLM4Vis, a novel ChatGPT-based prompting approach to perform visualization recommendation and return human-like explanations using very few demonstration examples. Our approach involves feature description, demonstration example selection, explanation generation, demonstration example construction, and inference steps. To …

Go to article

Graph Contrastive Learning With Stable And Scalable Spectral Encoding, Deyu Bo, Yuan Fang, Yang Liu, Chuan Shi Dec 2023

Graph Contrastive Learning With Stable And Scalable Spectral Encoding, Deyu Bo, Yuan Fang, Yang Liu, Chuan Shi

Research Collection School Of Computing and Information Systems

Graph contrastive learning (GCL) aims to learn representations by capturing the agreements between different graph views. Traditional GCL methods generate views in the spatial domain, but it has been recently discovered that the spectral domain also plays a vital role in complementing spatial views. However, existing spectral-based graph views either ignore the eigenvectors that encode valuable positional information, or suffer from high complexity when trying to address the instability of spectral features. To tackle these challenges, we first design an informative, stable, and scalable spectral encoder, termed EigenMLP, to learn effective representations from the spectral features. Theoretically, EigenMLP is invariant …

Go to article

Memory Network-Based Interpreter Of User Preferences In Content-Aware Recommender Systems, Nhu Thuat Tran, Hady W. Lauw Dec 2023

Memory Network-Based Interpreter Of User Preferences In Content-Aware Recommender Systems, Nhu Thuat Tran, Hady W. Lauw

Research Collection School Of Computing and Information Systems

This article introduces a novel architecture for two objectives recommendation and interpretability in a unified model. We leverage textual content as a source of interpretability in content-aware recommender systems. The goal is to characterize user preferences with a set of human-understandable attributes, each is described by a single word, enabling comprehension of user interests behind item adoptions. This is achieved via a dedicated architecture, which is interpretable by design, involving two components for recommendation and interpretation. In particular, we seek an interpreter, which accepts holistic user’s representation from a recommender to output a set of activated attributes describing user preferences. …

Go to article

Video Sentiment Analysis For Child Safety, Yee Sen Tan, Nicole Anne Huiying Teo, Ezekiel En Zhe Ghe, Jolie Zhi Yi Fong, Zhaoxia Wang Dec 2023

Video Sentiment Analysis For Child Safety, Yee Sen Tan, Nicole Anne Huiying Teo, Ezekiel En Zhe Ghe, Jolie Zhi Yi Fong, Zhaoxia Wang

Research Collection School Of Computing and Information Systems

The proliferation of online video content underscores the critical need for effective sentiment analysis, particularly in safeguarding children from potentially harmful material. This research addresses this concern by presenting a multimodal analysis method for assessing video sentiment, categorizing it as either positive (child-friendly) or negative (potentially harmful). This method leverages three key components: text analysis, facial expression analysis, and audio analysis, including music mood analysis, resulting in a comprehensive sentiment assessment. Our evaluation results validate the effectiveness of this approach, making significant contributions to the field of video sentiment analysis and bolstering child safety measures. This research serves as a …

Go to article

Large Language Model Is Not A Good Few-Shot Information Extractor, But A Good Reranker For Hard Samples!, Yubo Ma, Yixin Cao, Yongchin Hong, Aixin Sun Dec 2023

Large Language Model Is Not A Good Few-Shot Information Extractor, But A Good Reranker For Hard Samples!, Yubo Ma, Yixin Cao, Yongchin Hong, Aixin Sun

Research Collection School Of Computing and Information Systems

Large Language Models (LLMs) have made remarkable strides in various tasks. However, whether they are competitive few-shot solvers for information extraction (IE) tasks and surpass fine-tuned small Pre-trained Language Models (SLMs) remains an open problem. This paper aims to provide a thorough answer to this problem, and moreover, to explore an approach towards effective and economical IE systems that combine the strengths of LLMs and SLMs. Through extensive experiments on nine datasets across four IE tasks, we show that LLMs are not effective few-shot information extractors in general, given their unsatisfactory performance in most settings and the high latency and …

Go to article

Examining The Inter-Consistency Of Large Language Models: An In-Depth Analysis Via Debate, Kai Xiong, Xiao Ding, Yixin Cao, Ting Liu, Bing Qin Dec 2023

Examining The Inter-Consistency Of Large Language Models: An In-Depth Analysis Via Debate, Kai Xiong, Xiao Ding, Yixin Cao, Ting Liu, Bing Qin

Research Collection School Of Computing and Information Systems

Large Language Models (LLMs) have shown impressive capabilities in various applications, but they still face various inconsistency issues. Existing works primarily focus on the inconsistency issues within a single LLM, while we complementarily explore the inter-consistency among multiple LLMs for collaboration. To examine whether LLMs can collaborate effectively to achieve a consensus for a shared goal, we focus on commonsense reasoning, and introduce a formal debate framework (FORD) to conduct a three-stage debate among LLMs with real-world scenarios alignment: fair debate, mismatched debate, and roundtable debate. Through extensive experiments on various datasets, LLMs can effectively collaborate to reach a consensus …

Go to article

Robust Prompt Optimization For Large Language Models Against Distribution Shifts, Moxin Li, Wenjie Wang, Fuli Feng, Yixin Cao, Jizhi Zhang, Tat-Seng Chua Dec 2023

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

Research Collection School Of Computing and Information Systems

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

Go to article

Benchmarking Foundation Models With Language-Model-As-An-Examiner, Yushi Bai, Jiahao Ying, Yixin Cao, Xin Lv, Yuze He, Xiaozhi Wang, Jifan Yu, Kaisheng Zeng, Yijia Xiao, Haozhe Lyu, Jiayin Zhang, Juanzi Li, Lei Hou Dec 2023

Benchmarking Foundation Models With Language-Model-As-An-Examiner, Yushi Bai, Jiahao Ying, Yixin Cao, Xin Lv, Yuze He, Xiaozhi Wang, Jifan Yu, Kaisheng Zeng, Yijia Xiao, Haozhe Lyu, Jiayin Zhang, Juanzi Li, Lei Hou

Research Collection School Of Computing and Information Systems

Numerous benchmarks have been established to assess the performance of foundation models on open-ended question answering, which serves as a comprehensive test of a model’s ability to understand and generate language in a manner similar to humans. Most of these works focus on proposing new datasets, however, we see two main issues within previous benchmarking pipelines, namely testing leakage and evaluation automation. In this paper, we propose a novel benchmarking framework, Language-Model-as-an-Examiner, where the LM serves as a knowledgeable examiner that formulates questions based on its knowledge and evaluates responses in a reference-free manner. Our framework allows for effortless extensibility …

Go to article

Molca: Molecular Graph-Language Modeling With Cross-Modal Projector And Uni-Modal Adapter, Zhiyuan Liu, Sihang Li, Yanchen Luo, Hao Fei, Yixin Cao, Kenji Kawaguchi, Xiang Wang, Tat-Seng Chua Dec 2023

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

Research Collection School Of Computing and Information Systems

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

Go to article

First Prev Next Last