Digital Commons Network^™

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

Research Collection School Of Computing and Information Systems

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

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

Research Collection School Of Computing and Information Systems

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

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

Research Collection School Of Computing and Information Systems

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

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

Research Collection School Of Computing and Information Systems

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

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

Research Collection Yong Pung How School Of Law

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

Performing Information Extraction For Mission Engineering Applications, Samuel R. Koski

Engineering Management & Systems Engineering Theses & Dissertations

The process of extracting structured data from unstructured and semi-structured text is manual, time consuming and error prone. Current natural language processing approaches for automating this process are difficult to verify for non-trivial and context-sensitive corpora. Large Language Models (LLMs) like ChatGPT have become a subject of considerable interest, opening a promising avenue of exploration. However, there is limited evidence on the performance of LLMs for information extraction.

In this dissertation, an approach is proposed to evaluate the accuracy of Stanford OpenIE and OpenAI's ChatGPT for this purpose. This includes comparing Resource Description Framework (RDF) triples extracted by each of …

Differences In Biology Students’ Self-Regulation During Online And Offline Learning And Its Relationship To Learning Outcomes, Adi Kus Rochman Jk, Dwi Listyorini, Fatchur Rohman, Yessi Affriyenni

Jurnal Pendidikan Sains

The cultivation of self-regulatory skills holds paramount importance for individuals’ future success, particularly in the context of evolving educational modalities prompted by the Covid-19 pandemic. As learning transitions between online during the pandemic and offline post-pandemic, understanding the nuances of self-regulation becomes imperative. Thus, this study sought to achieve three objectives: (1) analyzing disparities in student self-regulation between online and offline settings, (2) examining the interplay between online and offline self-regulation, and (3) scrutinizing the relationship between self-regulation and learning outcomes. Employing a methodological approach involving questionnaire administration, interviews, and collecting academic scores data, data analysis was conducted utilizing the …

Individual Behavioral Modeling Across Games Of Strategy, Logan Fields

USF Tampa Graduate Theses and Dissertations

An individual’s actions in a particular environment and with specified resources can reveal their decision-making tendencies and patterns, and by analyzing the variations in cognitive traits among individuals, it may be possible to identify trends that can foretell their future behaviors. This can be a powerful tool in various fields including cognitive modeling, player analytics, computer security, and threat detection. Collectible card games are a fruitful test space for studying cognitive differences in decision-making, as they can have clearly defined and replicable environments and large player bases. As such, in this work, I explore the potential of using two virtual …

Preserving Linguistic Diversity In The Digital Age: A Scalable Model For Cultural Heritage Continuity, James Hutson, Pace Ellsworth, Matt Ellsworth

Faculty Scholarship

In the face of the rapid erosion of both tangible and intangible cultural heritage globally, the urgency for effective, wide-ranging preservation methods has never been greater. Traditional approaches in cultural preservation often focus narrowly on specific niches, overlooking the broader cultural tapestry, particularly the preservation of everyday cultural elements. This article addresses this critical gap by advocating for a comprehensive, scalable model for cultural preservation that leverages machine learning and big data analytics. This model aims to document and archive a diverse range of cultural artifacts, encompassing both extraordinary and mundane aspects of heritage. A central issue highlighted in the …

Intelligent Algorithm Safety: Concepts, Scientific Problems And Prospects, Xueqi Cheng, Wei Chen, Huawei Shen, Shiguang Shan, Xilin Chen, Guojie Li

Bulletin of Chinese Academy of Sciences (Chinese Version)

Intelligent algorithms refer to the methods embodied in the computational processes that realize intelligence. These methods are often characterized by being data-driven, involving uncertain computations, and with unexplainable model inferences. These characteristics simultaneously introduce potential safety risks to the application of intelligent algorithms and AI. This study firstly explores the concepts of intelligent algorithm safety. Specifically, intelligent algorithm safety, based on the degree of human-machine integration, extends from the univariate safety of the algorithm itself to the bivariate applicational safety when the algorithm serves humans, and finally evolves into the multivariate systemic safety arises within complex socio-technical systems of human-machine …

Breaking Through “Data Bottleneck” Of Ai Large Models—Reflections On Building A National Corpus Operation Platform, Xingteng Li, Feng Feng, Liqiang Huang

Bulletin of Chinese Academy of Sciences (Chinese Version)

At present, the competition within the global artificial intelligence (AI) large model industry is intensifying, and corpus resources emerging as a critical determinant for enhancing the technical performance and practical efficacy of AI systems. Nevertheless, China’s corpus development faces dual challenges in both quantity and quality, struggling to meet the escalating training demands of the rapidly evolving AI large model sector. Internationally, nations are ramping up efforts to develop their corpus infrastructures, particularly prioritizing the creation and deployment of high-quality linguistic datasets. In this context, through comparative analysis of international benchmarks and domestic conditions, this study proposes a strategic framework …

Using Chatgpt To Generate Gendered Language, Shweta Soundararajan, Manuela Nayantara Jeyaraj, Sarah Jane Delany

Conference papers

Gendered language is the use of words that denote an individual's gender. This can be explicit where the gender is evident in the actual word used, e.g. mother, she, man, but it can also be implicit where social roles or behaviours can signal an individual's gender - for example, expectations that women display communal traits (e.g., affectionate, caring, gentle) and men display agentic traits (e.g., assertive, competitive, decisive). The use of gendered language in NLP systems can perpetuate gender stereotypes and bias. This paper proposes an approach to generating gendered language datasets using ChatGPT which will provide data for data-driven …

Predicting Gender Of Author Using Large Language Models (Llms), Satya Uday Sanku

USF Tampa Graduate Theses and Dissertations

The advent of text data from social media, blogs, movie reviews, and other textual sources has opened new avenues for research, particularly in the domain of Author Profiling. Author Profiling helps in Capturing the Stylistic features and also useful for analyzing the required elements in the written text. This Study addresses one of the tasks in Author Profiling which is termed as gender detection or Classification of Gender from Text. The main goal of this research is to obtain valuable and relevant gender characteristics that will accurately classify the Author’s gender of a review extracted from an Anime Review website. …

Reclaiming The Symbol: Ethics, Rhetoric, And The Humanistic Integration Of Gai - A Burkean Perspective, Daniel Plate, James Hutson

Faculty Scholarship

This study delves into the intersection of generative artificial intelligence (GAI) and the Humanities, guided by the critical insights of Kenneth Burke, a seminal figure in the study of rhetoric and a vocal critic of scientism and positivism. The skepticism of the American literary theorist towards an uncritical embrace of science and technology, and his concerns over the inclination of the Humanities to adopt scientific methodologies at the expense of traditional forms of inquiry, provide a critical framework for examining the new role played by GAI within the Humanities. By framing these tools in the context of Burkean rhetorical theory, …

Learning About Ai: Level Up Your Skills Without Overwhelming Your Mind, Jennifer Freer, Lara Nicosia

Presentations and other scholarship

OpenAI and deep learning and neural networks, oh my!  The swiftly developing landscape of artificial intelligence, combined with its rapid integration into our work and personal lives, can feel confusing and overwhelming.  This session will help you think about AI in your own work and plan your own personal AI learning journey, while also providing thoughtful recommendations on how both you and your users can get started.  The presenters will discuss common terminology, user-friendly resources for understanding AI, questions to ask when exploring AI tools, and ideas on how to start building your own knowledge on this topic.  The information …

Western Science And Eastern Zen To Seek The Origin Of Truth: Philosophical Background Of Scale Modeling, Kozo Saito

Progress in Scale Modeling, an International Journal

This article was written to introduce philosophical background of scale modeling, where Zen philosophy was applied to overcome the limitation of logical thinking and hypotheses-driven deductive science. Three specific reasons are as follows. The first is related to the law approach in scale modeling; it uses the kufu principle, originated in Zen Buddhism, together with the other three scientific methods: experimental, theoretical, and computational. The second reason is because scale modeling seeks relativistic understanding by attempting to realize similarity; the concept is closer to Eastern philosophy rather than absolute understanding cultivated by deductive science. The third is in the educational …

How Can Generative Ai (Genai) Enhance Or Hinder Qualitative Studies? A Critical Appraisal From South Asia, Nepal, Niroj Dahal

The Qualitative Report

Qualitative researchers can benefit from using generative artificial intelligence (GenAI), such as different versions of ChatGPT—GPT-3.5 or GPT-4, Google Bard—now renamed as a Gemini, and Bing Chat—now renamed as a Copilot, in their studies. The scientific community has used artificial intelligence (AI) tools in various ways. However, using GenAI has generated concerns regarding potential research unreliability, bias, and unethical outcomes in GenAI-generated research results. Considering these concerns, the purpose of this commentary is to review the current use of GenAI in qualitative research, including its strengths, limitations, and ethical dilemmas from the perspective of critical appraisal from South Asia, Nepal. …

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

Research Collection Lee Kong Chian School Of Business

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

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

Research Collection School Of Computing and Information Systems

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

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

Research Collection School Of Computing and Information Systems

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

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

Research Collection School Of Computing and Information Systems

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

Improving Automatic Transcription Using Natural Language Processing, Anna Kiefer

Master's Theses

Digital Democracy is a CalMatters and California Polytechnic State University initia-
tive to promote transparency in state government by increasing access to the Califor-
nia legislature. While Digital Democracy is made up of many resources, one founda-
tional step of the project is obtaining accurate, timely transcripts of California Senate
and Assembly hearings. The information extracted from these transcripts provides
crucial data for subsequent steps in the pipeline. In the context of Digital Democracy,
upleveling is when humans verify, correct, and annotate the transcript results after
the legislative hearings have been automatically transcribed. The upleveling process
is done with the …

Spec: A Soft Prompt-Based Calibration On Performance Variability Of Large Language Model In Clinical Notes Summarization, Yu-Neng Chuang, Ruixiang Tang, Xiaoqian Jiang, Xia Hu

Faculty, Staff and Student Publications

Electronic health records (EHRs) store an extensive array of patient information, encompassing medical histories, diagnoses, treatments, and test outcomes. These records are crucial for enabling healthcare providers to make well-informed decisions regarding patient care. Summarizing clinical notes further assists healthcare professionals in pinpointing potential health risks and making better-informed decisions. This process contributes to reducing errors and enhancing patient outcomes by ensuring providers have access to the most pertinent and current patient data. Recent research has shown that incorporating instruction prompts with large language models (LLMs) substantially boosts the efficacy of summarization tasks. However, we show that this approach also …

A Novel Fuzzy Time Series Forecasting Method Based On Probabilistic Fuzzy Set And Cpbd Approach, Krishna Kumar Gupta, Suneet Saxena

Applications and Applied Mathematics: An International Journal (AAM)

Probabilistic fuzzy set is used to model the non-probabilistic and probabilistic uncertainties simultaneously in the system. This study proposes a cumulative probability-based discretization and probabilistic fuzzy set based novel fuzzy time series forecasting method. It also proposes a novel discretization approach based on cumulative probability to tackle the probabilistic uncertainty in partitioning of datasets. Gaussian probability distribution function has been used to construct probabilistic fuzzy set. The advantage of the proposed work is that it addresses the uncertainties due to randomness and fuzziness simultaneously and also improves accuracy rate in time series forecasting. A proposed forecasting method is applied on …

Measuring The Presentation Of Supporting Content For A Set Of Learning Objectives Throughout The States Of An Educational Game Tree, Michael L. Hastriter Jr.

Theses and Dissertations

In an era of evolving warfare, the Department of Defense (DoD) recognizes the value of serious games as immersive tools for teaching critical concepts. This thesis introduces a pioneering framework tailored to enhance learning objectives through the presentation of educational game content. This addresses the unique needs of the DoD and other educators who use games by providing measurements to assess educational games. This researches investigates how instructors might assess games as potential teaching tools. It establishes a five-phase process, providing a framework to assess educational games against predefined learning objectives and informing future game development. This thesis demonstrates games …

A Staged Framework For Llm-Powered Information Extraction In Government Contracts, Jung H. Yae

Theses and Dissertations

The manual extraction of meaningful insights and conversion of content into structured forms to enhance document processing require substantial resources and are susceptible to errors. Despite numerous applications of various Natural Language Processing (NLP) models to streamline the manual process, challenges persist due to domain-specific data constraints and the deficiency of annotated data. This study attempts to address these challenges by leveraging a Large Language Model (LLM) to analyze government contracts. Through rigorous evaluation, we demonstrate the LLM’s effectiveness in information extraction and mitigating hallucinations, achieving a 87.86% accuracy in metadata extraction.

Artificial Intelligence And Perception: An Empirical Study, Anthony J. Neil

Theses and Dissertations

This thesis investigates the impact of adjusting artificial intelligence explainability levels’ outputs on user perception. The overarching study extends within the Explainable Artificial Intelligence (XAI) domain. It examines a spectrum of variables, including performance, cognizance, familiarity, transparency, system bias, and the overall impact of AI, to understand their collective and individual effects that enable effective professional use in an organization. The study aims to illuminate the relationship between the degree of explainability provided by large language models such as ChatGPT, Bard, and Bing AI and the performance of these models when tasked with XAI adjustments.

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

Research Collection School Of Computing and Information Systems

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

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

Research Collection School Of Computing and Information Systems

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

Understanding The Impact Of Trade Policy Effect Uncertainty On Firm-Level Innovation Investment: A Deep Learning Approach, Daniel Chang, Nan Hu, Peng Liang, Morgan Swink

Research Collection School Of Computing and Information Systems

Integrating the real options perspective and resource dependence theory, this study examines how firms adjust their innovation investments to trade policy effect uncertainty (TPEU), a less studied type of firm specific, perceived environmental uncertainty in which managers have difficulty predicting how potential policy changes will affect business operations. To develop a text-based, context-dependent, time-varying measure of firm-level perceived TPEU, we apply Bidirectional Encoder Representations from Transformers (BERT), a state-of-the-art deep learning approach. We apply BERT to analyze the texts of mandatory Management Discussion and Analysis (MD&A) sections of annual reports for a sample of 22,669 firm-year observations from 3,181 unique …