Open Access. Powered by Scholars. Published by Universities.®
- Institution
-
- Singapore Management University (1116)
- TÜBİTAK (210)
- Wright State University (197)
- Technological University Dublin (193)
- University of New Mexico (165)
-
- Old Dominion University (143)
- Claremont Colleges (126)
- Missouri University of Science and Technology (125)
- University of Nebraska - Lincoln (123)
- San Jose State University (119)
- City University of New York (CUNY) (115)
- Brigham Young University (105)
- Neutrosophic Systems with Applications (89)
- University of Texas at El Paso (88)
- University of Northern Iowa (78)
- University of South Florida (77)
- Chulalongkorn University (73)
- Dartmouth College (71)
- MBZUAI (70)
- Kennesaw State University (64)
- Portland State University (60)
- Zayed University (58)
- Chapman University (57)
- New Jersey Institute of Technology (57)
- Boise State University (56)
- Edith Cowan University (54)
- University of Arkansas, Fayetteville (54)
- University of Nevada, Las Vegas (53)
- Purdue University (51)
- Montclair State University (49)
- Keyword
-
- Natural language processing (209)
- Machine learning (208)
- Artificial intelligence (154)
- Natural Language Processing (148)
- Machine Learning (143)
-
- Deep learning (130)
- Artificial Intelligence (97)
- Large language models (88)
- Social media (83)
- Computer Science (82)
- NLP (74)
- Twitter (70)
- Sentiment analysis (69)
- Mathematics (68)
- Deep Learning (66)
- Large Language Models (61)
- Text mining (59)
- Neural networks (58)
- Computational linguistics (54)
- Department of Computer Science and Engineering (53)
- Computer science (52)
- Education (49)
- Fuzzy logic (49)
- AI (47)
- Data mining (47)
- Generative AI (46)
- Linguistics (43)
- Classification (41)
- Social Media (39)
- Information retrieval (38)
- Publication Year
- Publication
-
- Research Collection School Of Computing and Information Systems (1033)
- Theses and Dissertations (222)
- Turkish Journal of Electrical Engineering and Computer Sciences (199)
- Branch Mathematics and Statistics Faculty and Staff Publications (150)
- Master's Projects (99)
-
- Conference papers (96)
- Neutrosophic Systems with Applications (89)
- Kno.e.sis Publications (84)
- Dissertations (83)
- Chulalongkorn University Theses and Dissertations (Chula ETD) (70)
- Computer Science Faculty Research & Creative Works (66)
- Electronic Theses and Dissertations (65)
- Journal of Humanistic Mathematics (63)
- Browse all Theses and Dissertations (62)
- Faculty Publications (59)
- All Works (58)
- Computer Science Faculty Publications (58)
- USF Tampa Graduate Theses and Dissertations (55)
- Publications and Research (51)
- Iowa Academy of Science Documents (50)
- Computer Science Faculty Publications and Presentations (45)
- Departmental Technical Reports (CS) (44)
- Dissertations, Theses, and Capstone Projects (43)
- Articles (42)
- Faculty, Staff and Student Publications (42)
- Open Access Theses & Dissertations (42)
- SMU Data Science Review (41)
- Walden Dissertations and Doctoral Studies (39)
- Computer Science and Engineering Faculty Publications (38)
- Natural Language Processing Faculty Publications (38)
- Publication Type
- File Type
Articles 451 - 480 of 6234
Full-Text Articles in Entire DC Network
Sheetpedia: A 300k-Spreadsheet Corpus For Spreadsheet Intelligence And Llm Fine-Tuning, Zailong Tian, Zhuoheng Han, Houfeng Wang, Lizi Liao
Sheetpedia: A 300k-Spreadsheet Corpus For Spreadsheet Intelligence And Llm Fine-Tuning, Zailong Tian, Zhuoheng Han, Houfeng Wang, Lizi Liao
Research Collection School Of Computing and Information Systems
Spreadsheets are widely used for data analysis and reporting, yet their complex structure and formula logic pose significant challenges for AI systems. We introduce Sheetpedia, a large-scale corpus of over 290,000 diverse spreadsheets (from 324,000+ workbooks) compiled from enterprise email archives and online forums. We detail a rigorous collection and preprocessing pipeline (integrating the Enron email spreadsheet archive and the Fuse web corpus, plus a new crawl of Excel forums) to standardize formats, filter languages, and remove duplicates. Sheetpedia provides extensive coverage of real formulas and annotations – addressing a gap left by prior table datasets (e.g. web tables used …
Contx: Scene Context Prediction Via Context Bank And Layout Perception, Jingxin Liang, Yangyang Xu, Haorui Song, Yuan Lu, Yuhui Deng, Yiyi Long, Yan Huang, Shengxin Liu, Jianbo Jiao, Shengfeng He
Contx: Scene Context Prediction Via Context Bank And Layout Perception, Jingxin Liang, Yangyang Xu, Haorui Song, Yuan Lu, Yuhui Deng, Yiyi Long, Yan Huang, Shengxin Liu, Jianbo Jiao, Shengfeng He
Research Collection School Of Computing and Information Systems
Scene context prediction, which seeks to infer unknown contextual information from isolated object properties, currently faces limitations due to predominant reliance on pixel-wise supervision that overlooks real-world context priors. To address this, we present ContX, a context-prior-driven, coarse-to-fine model. ContX distinctively integrates explicit linguistic-contextual knowledge in two key ways. First, it proposes a linguistic guided context bank, leveraging linguistic-statistical contextual data to guide the rationality of segmentation shapes and foster meaningful inter-class contextual interactions. Second, ContX augments contextual comprehension by correlating layouts with linguistic descriptions, enhancing layout perception through a multi-modal strategy. Comprehensive experiments demonstrate ContX's superiority and versatility, outperforming …
Backdoorllm: A Comprehensive Benchmark For Backdoor Attacks And Defenses On Large Language Models, Yige Li, Hanxun Huang, Yunhan Zhao, Xingjun Ma, Jun Sun
Backdoorllm: A Comprehensive Benchmark For Backdoor Attacks And Defenses On Large Language Models, Yige Li, Hanxun Huang, Yunhan Zhao, Xingjun Ma, Jun Sun
Research Collection School Of Computing and Information Systems
Generative large language models (LLMs) have achieved state-of-the-art results on a wide range of tasks, yet they remain susceptible to backdoor attacks: carefully crafted triggers in the input can manipulate the model to produce adversaryspecified outputs. While prior research has predominantly focused on backdoor risks in vision and classification settings, the vulnerability of LLMs in open-ended text generation remains underexplored. To fill this gap, we introduce BackdoorLLM1 , the first comprehensive benchmark for systematically evaluating backdoor threats in text-generation LLMs. BackdoorLLM provides: (i) a unified repository of benchmarks with a standardized training and evaluation pipeline; (ii) a diverse suite of …
Large Language Models As End-To-End Combinatorial Optimization Solvers, Xia Jiang, Yaoxin Wu, Minshuo Li, Zhiguang Cao, Yingqian Zhang
Large Language Models As End-To-End Combinatorial Optimization Solvers, Xia Jiang, Yaoxin Wu, Minshuo Li, Zhiguang Cao, Yingqian Zhang
Research Collection School Of Computing and Information Systems
Combinatorial optimization (CO) problems, central to decision-making scenarios like logistics and manufacturing, are traditionally solved using problem-specific algorithms requiring significant domain expertise. While large language models (LLMs) have shown promise in automating CO problem solving, existing approaches rely on intermediate steps such as code generation or solver invocation, limiting their generality and accessibility. This paper introduces a novel framework that empowers LLMs to serve as end-to-end CO solvers by directly mapping natural language problem descriptions to solutions. We propose a two-stage training strategy: supervised fine-tuning (SFT) imparts LLMs with solution generation patterns from domain-specific solvers, while a feasibility-and-optimality-aware reinforcement learning …
Sciteuq: Toward Uncertainty-Aware Complex Scientific Table Data Extraction And Understanding, Kehinde Ajayi
Sciteuq: Toward Uncertainty-Aware Complex Scientific Table Data Extraction And Understanding, Kehinde Ajayi
Computer Science Theses & Dissertations
Scientific tables report critical research insights, data, and findings for scientific progress. Because Portable Document Format (PDF) is the de facto standard format for scientific paper publishing, there has been an emerging need for an automatic method to extract data from PDF files. A significant fraction of scientific tables exhibit complex structure and content, making it challenging for machine learning tools to accurately extract the content directly from PDF files. Despite the advancements in Table Structure Recognition (TSR), automated extraction of data from complex scientific tables remains a challenge due to variations in table structures and contents. In this dissertation, …
Multi-Task Vehicle Routing Solver Via Mixture Of Specialized Experts Under State-Decomposable Mdp, Yuxin Pan, Zhiguang Cao, Chengyang Gu, Liu Liu, Peilin Zhao, Yize Chen, Fangzhen Lin
Multi-Task Vehicle Routing Solver Via Mixture Of Specialized Experts Under State-Decomposable Mdp, Yuxin Pan, Zhiguang Cao, Chengyang Gu, Liu Liu, Peilin Zhao, Yize Chen, Fangzhen Lin
Research Collection School Of Computing and Information Systems
Existing neural methods for multi-task vehicle routing problems (VRPs) typically learn unified solvers to handle multiple constraints simultaneously. However, they often underutilize the compositional structure of VRP variants, each derivable from a common set of basis VRP variants. This critical oversight causes unified solvers to miss out the potential benefits of basis solvers, each specialized for a basis VRP variant. To overcome this limitation, we propose a framework that enables unified solvers to perceive the shared-component nature across VRP variants by proactively reusing basis solvers, while mitigating the exponential growth of trained neural solvers. Specifically, we introduce a State-Decomposable MDP …
When Less Language Is More: Language-Reasoning Disentanglement Makes Llms Better Multilingual Reasoners, Weixiang Zhao, Jiahe Guo, Yang Deng, Tongtong Wu, Wenxuan Zhang, Yulin Hu, Xingyu Sui, Yanyan Zhao, Wanxiang Che, Bing Qin, Tat-Seng Chua, Ting Liu
When Less Language Is More: Language-Reasoning Disentanglement Makes Llms Better Multilingual Reasoners, Weixiang Zhao, Jiahe Guo, Yang Deng, Tongtong Wu, Wenxuan Zhang, Yulin Hu, Xingyu Sui, Yanyan Zhao, Wanxiang Che, Bing Qin, Tat-Seng Chua, Ting Liu
Research Collection School Of Computing and Information Systems
Multilingual reasoning remains a significant challenge for large language models (LLMs), with performance disproportionately favoring high-resource languages. Drawing inspiration from cognitive neuroscience, which suggests that human reasoning functions largely independently of language processing, we hypothesize that LLMs similarly encode reasoning and language as separable components that can be disentangled to enhance multilingual reasoning. To evaluate this, we perform a causal intervention by ablating language-specific representations at inference time. Experiments on 10 open-weight LLMs spanning 11 typologically diverse languages show that this language-specific ablation consistently boosts multilingual reasoning performance. Layer-wise analyses further confirm that language and reasoning representations can be effectively …
Transdisciplinary Perspectives On Ai: The Fourth Annual Conference Of The European Culture And Technology Laboratory, Connell Vaughan, Ioana Madalina Moldovan, Silivan Moldovan, Noel Fitzpatrick
Transdisciplinary Perspectives On Ai: The Fourth Annual Conference Of The European Culture And Technology Laboratory, Connell Vaughan, Ioana Madalina Moldovan, Silivan Moldovan, Noel Fitzpatrick
Books/Book Chapters
The fourth annual conference of the ECT Lab+ was hosted by Technical University of Cluj-Napoca over two days in October 2024 at the Cluj Innovation Park. The conference brought together experts from the Arts, Humanities, Social Sciences, Technology, and other fields to discuss and reflect on the advent of Artificial Intelligence and how the associated technologies are transforming how we live, work and study. Under the title Transdisciplinary perspectives on AI: Alternative Histories, Current Practices and Possible Futures the conference moved beyond simplistic technophila and technophobia to consider whether we can co-evolve with these new technologies which combine machine learning …
Grm-20169 Proxy Recognition And Inclusive Scoring Method (Prism): Evaluating Context-Dependent Bias In Large Language Models For Resume Screening, Crystal Tubbs, Destiny Raburnel
Grm-20169 Proxy Recognition And Inclusive Scoring Method (Prism): Evaluating Context-Dependent Bias In Large Language Models For Resume Screening, Crystal Tubbs, Destiny Raburnel
C-Day Computing Showcase
AI-driven hiring tools are reshaping recruitment but often mirror biases in their training data. PRISM examines how large language models express or reduce demographic bias during resume evaluation and how linguistic context within prompts shapes these outcomes. Using a controlled dataset of 324 synthetic resumes with racially neutral surnames, differing only by first name as the demographic proxy, we compared GPT 3.5 turbo with a Sentence BERT similarity model. Under neutral prompts, no stable bias was observed across demographic groups, yet contextual shifts in the prompt changed how the model responded to proxy cues. These findings show that LLM bias …
Ai-Powered Compliance: Accelerating Efficiency And Decision-Making For Compliance Related Inquiries., Amberly R. Rodriguez
Ai-Powered Compliance: Accelerating Efficiency And Decision-Making For Compliance Related Inquiries., Amberly R. Rodriguez
SMU Data Science Review
This research examines the potential of an AI-powered chatbot to streamline compliance workflows by reducing the time and effort required to locate and interpret complex compliance documents. The prototype integrates a centralized MySQL-based document repository, a contextual document querying engine, and a Streamlit web interface, enabling employees to retrieve accurate, document-backed answers within seconds. The system supports both stored and user-uploaded documents, with features such as automated summarization and source citations to enhance transparency and trust. Manual evaluation demonstrated notable gains in efficiency and accuracy compared to traditional search methods, with strong potential to improve adherence to compliance policies. Future …
Analyzing The Global Happiness Index, Victoria Hernandez, Christy W. Wachira
Analyzing The Global Happiness Index, Victoria Hernandez, Christy W. Wachira
SMU Data Science Review
This study explores the Global Happiness Index using data compiled from the OECD and Our World in Data to identify key factors contributing to societal well-being. Six primary predictors were analyzed: GDP per capita, social support, healthy life expectancy, freedom to make life choices, generosity, and perceptions of corruption. Regression and clustering techniques were employed to uncover patterns among countries. By expanding the analytical scope beyond conventional economic and social indicators, this study helps identify new pathways for improving well-being across diverse cultural and economic landscapes. Additional variables such as perceived safety, political engagement, and values related to family and …
A Decolonial Approach To International Education: Insights From A Cal Poly Global Program In Palermo, Sicily., Elvira Pulitano, Iyad Jamaly
A Decolonial Approach To International Education: Insights From A Cal Poly Global Program In Palermo, Sicily., Elvira Pulitano, Iyad Jamaly
csuglobaljournal
This article presents a critical intervention in the current debates about decolonizing international education. It is based on a Global Program in Palermo, Sicily, offered by Cal Poly San Luis Obispo in summer 2023. As both program creator/director and student participant in the program, the authors rely on their personal experience and insights along with expertise in coloniality and decolonial theories. The article focuses on a series of pedagogical activities led by a young group of migrants and refugees who, in the city of Palermo, have come together to form two associations designed and structured to offer new contemporary models …
When Scripts Diverge: Strengthening Low-Resource Neural Machine Translation Through Phonetic Cross-Lingual Transfer, Ammon Shurtz
When Scripts Diverge: Strengthening Low-Resource Neural Machine Translation Through Phonetic Cross-Lingual Transfer, Ammon Shurtz
Theses and Dissertations
Multilingual Neural Machine Translation (MNMT) models enhance translation quality for low-resource languages by exploiting cross-lingual similarities during training--a process known as knowledge transfer. This transfer is particularly effective between languages that share lexical or structural features, often enabled by a common orthography. However, languages with strong phonetic and lexical similarities but distinct writing systems experience limited benefits, as the absence of a shared orthography hinders knowledge transfer. To address this limitation, we propose an approach based on phonetic information that enhances token-level alignment across scripts by leveraging transliterations. We systematically evaluate several phonetic transcription techniques and strategies for incorporating phonetic …
Climatology Of Northeast Winds In Northern And Central California: A New Characterization Of The Diablo Wind, Alana R. Macken
Climatology Of Northeast Winds In Northern And Central California: A New Characterization Of The Diablo Wind, Alana R. Macken
Master's Theses
Diablo winds in northern California are known for driving some of the most destructive wildfires in state history. The Camp Fire of 2018, which caused at least 85 civilian fatalities, is just one example of the devastating outcomes associated with these rapidly developing downslope windstorms. While they are known to occur most frequently from fall through spring, much about the structure, evolution, and full spatial extent of these events remains poorly understood. Most previous studies have focused on a limited number of high-impact cases or have defined events using humidity-based thresholds in isolated regions such as the North Bay. As …
Cv: Cynthia Howard (Computer Science), Cynthia Howard
Cv: Cynthia Howard (Computer Science), Cynthia Howard
ECaMS Department Faculty Curricula Vitae
No abstract provided.
Efficient Multimodal Streaming Recommendation Via Expandable Side Mixture-Of-Experts, Yunke Qu, Liang Qu, Tong Chen, Quoc Viet Hung Nguyen, Hongzhi Yin
Efficient Multimodal Streaming Recommendation Via Expandable Side Mixture-Of-Experts, Yunke Qu, Liang Qu, Tong Chen, Quoc Viet Hung Nguyen, Hongzhi Yin
Research outputs 2022 to 2026
Streaming recommender systems (SRSs) are widely deployed in real-world applications, where user interests shift and new items arrive over time. As a result, effectively capturing users' latest preferences is challenging, as interactions reflecting recent interests are limited and new items often lack sufficient feedback. A common solution is to enrich item representations using multimodal encoders (e.g., BERT or ViT) to extract visual and textual features. However, these encoders are pretrained on general-purpose tasks: they are not tailored to user preference modeling, and they overlook the fact that user tastes toward modality-specific features such as visual styles and textual tones can …
Proactllm: Proactive Conversational Information Seeking With Large Language Models, Shubham Chatterjee, Xi Wang, Shuo Zhang, Sajad Ebrahimi, Zhaochun Ren, Debasis Ganguly, Gareth Jones, Emine Arrousse, Hamed Zamani
Proactllm: Proactive Conversational Information Seeking With Large Language Models, Shubham Chatterjee, Xi Wang, Shuo Zhang, Sajad Ebrahimi, Zhaochun Ren, Debasis Ganguly, Gareth Jones, Emine Arrousse, Hamed Zamani
Computer Science Faculty Research & Creative Works
Large Language Models (LLMs) have transformed information access by enabling human-like text understanding and generation. This workshop explores the next step for conversational AI: building proactive information-seeking assistants that go beyond reactive question answering. We aim to investigate how LLMs can anticipate user needs, model complex context, support mixed-initiative interactions, integrate retrieval and external tools, personalize responses, adapt through feedback, and ensure fairness, transparency, and cognitive grounding. Bringing together experts from NLP, IR, HCI, and cognitive science, the workshop will serve as a timely forum for advancing intelligent, proactive dialogue systems. It will also foster interdisciplinary collaboration.
Comprehensive Risk Evaluation Framework For Reducing Errors In Critical Airport Systems, Arshad Hameed, Muhammad Umer Farooq
Comprehensive Risk Evaluation Framework For Reducing Errors In Critical Airport Systems, Arshad Hameed, Muhammad Umer Farooq
Neutrosophic Systems with Applications
Airports are intricate systems that are subject to a number of operational hazards that might impair safety and cause service interruptions. There is a dearth of thorough approaches designed specifically for airport operations, despite a wealth of research on risk management in several industries. In order to anticipate and prevent breakdowns in vital airport systems, we offer a thorough risk assessment approach that combines quantitative evaluation and human factor analysis. This study uses the decision-making methodology such as MARCOS method to rank the alternatives. The criteria weights are computed in this study. This study uses six criteria and 14 alternatives.
Evaluating Solar Energy Challenges And Strategies To Overcome Challenges Under Neutrosophic Decision Making Methodology, Ahmed A El-Douh, Mina Samir Shenouda
Evaluating Solar Energy Challenges And Strategies To Overcome Challenges Under Neutrosophic Decision Making Methodology, Ahmed A El-Douh, Mina Samir Shenouda
Neutrosophic Systems with Applications
Because of its reliance on fossil fuels and fast population expansion, the nation confronts severe socioeconomic problems that can result in political instability, environmental damage, health issues, and economic instability. A switch to clean energy is now necessary as a result of these problems widening the gap between supply and demand for energy. To close this gap, photovoltaic (PV) technology holds great potential. In order to reduce bias and handle ambiguity while assessing solar energy (SE) issues and regulations, this study offers a decision-making process in a single valued neutrosophic set (SVNS) environment. The neutrosophic set is used to overcome …
An Analysis Of Large Language Model Hallucination And Creativity: Linear Representations And Causal Roles, Mckay Bowcut
An Analysis Of Large Language Model Hallucination And Creativity: Linear Representations And Causal Roles, Mckay Bowcut
Theses and Dissertations
Large language models (LLMs) show remarkable abilities in both factual and creative tasks, yet the problem of hallucination persists despite advances in training and post-training methods. Recent progress in model interpretability suggests that model behavior can be predicted and influenced by analyzing and manipulating internal activations. In this thesis, we address three questions: (1) Can we identify linear representations of hallucination and creativity in the model’s latent space? (2) Do these representations play a causal role in model behavior when manipulated? (3) Are creativity and hallucination causally intertwined? To answer these, we construct a novel dataset of factual, hallucinated, and …
Sound Practices In Human Resources: A Critical Analysis Of How Ai Applicant Screening Tools Are Used With Deaf Individuals In The Hospitality And Tourism Sector, Sherry L. Gaynor
Sound Practices In Human Resources: A Critical Analysis Of How Ai Applicant Screening Tools Are Used With Deaf Individuals In The Hospitality And Tourism Sector, Sherry L. Gaynor
USF Tampa Graduate Theses and Dissertations
This study explores the intersection of Career and Workforce Education, Deaf Education, and artificial intelligence (AI) technologies used in hiring practices. The purpose of this research is to identify potential barriers to equitable employment for Deaf and Hard-of-Hearing (DHH) individuals and to propose effective methods for evaluating and assessing AI and machine learning applications utilized in recruitment and selection processes. Although AI is increasingly embedded in human resource management (HRM), there remains a significant lack of research addressing its use with special populations. In particular, no prior studies have examined how voice recognition software, facial analysis, psychometric testing, and virtual …
Development Of E-Lkpd Assisted By Phet Colorado Basedon Discovery Learning: Critical Thinking Skills On Lightmaterial At Junior High School, Flora Yani Saragih, Pintor Simamora
Development Of E-Lkpd Assisted By Phet Colorado Basedon Discovery Learning: Critical Thinking Skills On Lightmaterial At Junior High School, Flora Yani Saragih, Pintor Simamora
Jurnal Pendidikan Sains
Critical thinking is necessary for 21st-century pupils, but PISA data suggest that Indonesian students, especially junior high school students, lack it. The junior high science/physics light material is abstract and involves in-depth reasoning (reflection, refraction, and shadow generation). Without critical thinking, kids memorize formulas or notions without analyzing real phenomena. Discovery learning involves pupils discovering concepts via observation and experimentation. Critical thinking requires initiative, exploration, and reasoning, which these foster. Therefore, this study aims to develop E-LKPD based on Discovery Learning assisted by an interactive simulation of PhET Colorado to strengthen the critical thinking skills of grade VIII students on …
Effects Of Code Scaffolding In Increasing Student Confidence In Programming Cryptography, John Denny
Effects Of Code Scaffolding In Increasing Student Confidence In Programming Cryptography, John Denny
LSU Master's Theses
Cryptography is essential for secure communications, and new threats require more students willing to program and interact with cryptographic systems. Previous research is focused on tools for teaching these systems at a high level, teaching through attacks against these systems, and proper use of these systems in software development. In this paper, we seek to design a workshop to use scaffolded Python code to teach how these cryp- tographic systems are designed. We explore the use of code scaffolding for students to program an example implementation of the McEliece crypto- graphic system to build confidence in working with these systems. …
Systematic Review Of Elementary Cybersecurity Education: Curriculum, Pedagogy, And Barriers, Na Liu, Siyu Long, Florence Martin
Systematic Review Of Elementary Cybersecurity Education: Curriculum, Pedagogy, And Barriers, Na Liu, Siyu Long, Florence Martin
Journal of Cybersecurity Education, Research and Practice
Abstract -As children increasingly engage with digital platforms, the need for effective cybersecurity education has become urgent. This systematic review synthesizes 81 studies published between 2017 and 2024 to examine global curricula research focus and topics, pedagogical approaches and assessment methods, and key challenges in elementary cybersecurity education. The findings reveal six major thematic categories: student awareness, parental mediation, teacher engagement, curriculum design, community and policy support, and pedagogical innovation. Among instructional strategies, game-based learning and narrative storytelling emerge as the most frequently explored. Despite this growth, major gaps remain in curriculum consistency, teacher preparation, assessment rigor, and stakeholder coordination. …
Composition Pedagogy As Ai‑Native Coding: From Design Kit To Scholarly Framework, Daniel Plate, James Hutson
Composition Pedagogy As Ai‑Native Coding: From Design Kit To Scholarly Framework, Daniel Plate, James Hutson
Faculty Scholarship
This article advances a field-ready framework that reconceives first-year composition as AI-native coding, translating a complete “design kit” into scholarly method, evaluative protocol, and curriculum architecture. Background: Contemporary composition pedagogy emphasizes process, genre awareness, and collaborative revision; meanwhile, modern software practice operationalizes iteration through version control, test-driven development, and continuous integration. The uploaded kit demonstrates that these cultures are isomorphic: writing stages align with SDLC phases, and automated pipelines can lint prose, execute argument “tests,” and publish artifacts with auditable histories. Approach: The study systematizes that kit into (1) a conceptual map that recasts authorship as orchestration and verification, (2) …
Do Code Semantics Help? A Comprehensive Study On Execution Trace-Based Information For Code Large Language Models, Jian Wang, Xiaofei Xie, Qiang Hu, Shangqing Liu, Yi Li
Do Code Semantics Help? A Comprehensive Study On Execution Trace-Based Information For Code Large Language Models, Jian Wang, Xiaofei Xie, Qiang Hu, Shangqing Liu, Yi Li
Research Collection School Of Computing and Information Systems
Code Large Language Models (Code LLMs) have opened a new era in programming with their impressive capabilities. However, recent research has revealed critical limitations in their ability to reason about runtime behavior and understand the actual functionality of programs, which poses significant challenges for their post-training and practical deployment. Specifically, Code LLMs encounter two principal issues: (1) a lack of proficiency in reasoning about program execution behavior, as they struggle to interpret what programs actually do during runtime, and (2) inconsistent and fragmented representation of semantic information, such as execution traces, across existing methods, which hinders their ability to generalize …
Efficient Integration Of External Knowledge To Llm-Based World Models Via Retrieval-Augmented Generation And Reinforcement Learning, Chang Yang, Xinrun Wang, Qinggang Zhang, Qi Jiang, Xiao Huang
Efficient Integration Of External Knowledge To Llm-Based World Models Via Retrieval-Augmented Generation And Reinforcement Learning, Chang Yang, Xinrun Wang, Qinggang Zhang, Qi Jiang, Xiao Huang
Research Collection School Of Computing and Information Systems
World models achieve remarkable success in predicting future states and planning in complex environments and Large Language Models (LLMs) serve as promising foundation to build general world models. However, their performances are usually constrained by the limited external knowledge to specific environments. Existing research attempts to enhance LLM-based world models through prompting or fine-tuning approaches, which are either requiring human knowledge or computationally extensive. Therefore, we introduce Retrieval-Augmented World Models (RAWM), a novel framework that leverages retrieval-augmented generation to efficiently integrate the external knowledge to LLM-based world models. Our main contributions are threefold: (i) We introduce a memory system and …
One Planner To Guide Them All! Learning Adaptive Conversational Planners For Goal-Oriented Dialogues, Huy Dao, Lizi Liao
One Planner To Guide Them All! Learning Adaptive Conversational Planners For Goal-Oriented Dialogues, Huy Dao, Lizi Liao
Research Collection School Of Computing and Information Systems
Goal-oriented dialogues, such as recommendation and negotiation, often require balancing multiple, conflicting objectives. Existing methods typically involve training separate models for specific combinations of objectives, leading to computational and scalability issues. In this work, we aim to develop a new dialogue policy method that can adapt to varying objective preferences at inference time without retraining. This raises several challenges in terms of both (1) optimization strategy and (2) knowledge utilization. To address these, we propose a novel learning framework, Preference Adaptive Dialogue Policy Planner (PADPP), for multi-objective goal-oriented dialogues. Specifically, to tackle the former, we introduce a novel policy optimization …
Gerunds In Irish Sign Language: An Exploratory Analysis, Zaid Mohammed
Gerunds In Irish Sign Language: An Exploratory Analysis, Zaid Mohammed
Doctoral
In sign languages (SLs), e.g., American Sign Language (ASL), gerunds help express the meaning of ongoing actions and activities conveyed by verbs (Klima & Bellugi, 1979, p. 295). In spoken languages, a gerund is a form of the verb that functions as a noun and expresses the state of being or an ongoing action (Maekelberghe, 2020). Gerunds are complex constructions as they have nominal-verbal nature (Travis, 2005, p. 321) and morphological similarity with present participle or progressive aspect (Siegel, 1998). This research is motivated by the challenging nature of distinguishing gerund constructions at the morphological level, and research in sign …
When It Comes To Scientific Information Extraction And Llms, Less Is More, Sameer Shaik
When It Comes To Scientific Information Extraction And Llms, Less Is More, Sameer Shaik
Theses and Dissertations from DePaul University
The scientific literature continues to expand rapidly, making manual extraction of structured scientific facts increasingly impractical. Traditional Machine Learning and Natural Language Processing (NLP) pipelines require large expert-annotated datasets, which are costly to produce. Novel Large Language Models (LLMs) face challenges in long-context scientific reasoning, hallucinations, and entity linking. This thesis investigates ELSIE-Blob, a domain-aware preprocessing method that segments scientific articles into compact text “blobs” containing components of entity relations (here, polymer names, melting point indicators, and numerical values). We test whether blob-based input allows lightweight, consumer-hardware-accessible LLMs to extract polymer–melting point (polymer–Tm) pairs accurately without training data. Experiments using …