Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 20 of 34 for “"GPT 3"”.

  1. Leveraging Large Language Models Trained on Code for Symbol Binding

    While large language models like GPT-3 have achieved impressive results in the zero-, one-, and few-shot settings, they still significantly underperform on some tasks relative to the state of the art (SOTA). For many tasks it would be useful to have answer options explicitly listed out in a …

    byu Repository record for Leveraging Large Language Models Trained on Code for Symbol Binding (opens in a new tab) Download PDF for Leveraging Large Language Models Trained on Code for Symbol Binding (opens in a new tab)

  2. An NLP approach to assess information security policies

    … focus was on the large-scale pre-trained model GPT-3 by OpenAI. Three different datasets were constructed to train the models, each consisting of annotated text extracts from information security policy. These were labeled as either being ISO certified or not, depending on if the company, or the …

    chalmers Repository record for An NLP approach to assess information security policies (opens in a new tab)

  3. Dispensing With Humans in Human-Computer Interaction Research

    … about and experiences with technology. We use GPT-3 and ChatGPT to replace human analysis and then to dispense with human-produced text altogether. We find GPT-3 is capable of automatically identifying themes and generating nuanced analyses of qualitative data arguably similar to those written …

    byu Repository record for Dispensing With Humans in Human-Computer Interaction Research (opens in a new tab) Download PDF for Dispensing With Humans in Human-Computer Interaction Research (opens in a new tab)

  4. Assessing the Effects and Risks of Large Language Models in AI-Mediated Communication

    Large language models like GPT-3 are increasingly becoming part of human communication. Through writing suggestions, grammatical assistance, and machine translation, the models enable people to communicate more efficiently. Yet, we have a limited understanding of how integrating them into …

    cornell Repository record for Assessing the Effects and Risks of Large Language Models in AI-Mediated Communication (opens in a new tab)

  5. Making Books with Generative AI

    … and book arts. Powerful new models like GPT-3 have the potential to transform creative workflows, raising questions around automation's role and preserving human craftsmanship. Through conceptual prototypes and speculative interfaces, this study reveals opportunities and critical …

    concordia Download PDF for Making Books with Generative AI (opens in a new tab)

  6. An Exploratory Study on the Roles of LLMs in Code Similarity Detection and Generation

    … the rise of large language models (LLMs) such as GPT, Gemini, and LLaMA, there is growing interest in leveraging their capabilities to improve clone detection, code generation, and cross-language translation. Despite this interest, research has yet to thoroughly evaluate how these models can be …

    sask Repository record for An Exploratory Study on the Roles of LLMs in Code Similarity Detection and Generation (opens in a new tab)

  7. Prompting LLMs for Zero-Shot Next-Item Recommendation

    … Our strategy uses a 4-step prompt to guide GPT-3 to learn the user’s preferences through the user’s past interaction history and recommend a ranked list of K movies. We evaluate the proposed method using GPT-3 on the MovieLens 100K dataset and show that it achieves strong zero-shot …

    tamu Repository record for Prompting LLMs for Zero-Shot Next-Item Recommendation (opens in a new tab)

  8. Exploring Trustworthiness Issues About Disaster-related Information Generated by Artificial Intelligence

    … trust or distrust. The thesis used OpenAI's GPT-3 model to generate stories based on real disaster events by artificial intelligence, and tested the degree of trustworthiness in semi-structured interview. The study showed that it was promising to use AI technology to publicize …

    south-carolina Repository record for Exploring Trustworthiness Issues About Disaster-related Information Generated by Artificial Intelligence (opens in a new tab)

  9. Empires of the Everyday

    … of Empire, colonialism, and state violence. Like GPT-3 technology, the voice is written as though trained on trillions of words of text derived from humans, making it individualized and of multiple registers. The poems often address multiple individuals of various subjectivities (“you”) moving …

    guelph Repository record for Empires of the Everyday (opens in a new tab) Embargoed until 2999-01-01

  10. EARLY SCREENING OF ALZHEIMER’S DISEASE THROUGH VERBAL COMMUNICATION AND USING LARGE LANGUAGE MODELS (LLMS)

    … of fine-tuned open-source models like LLaMA and GPT-3 was compared to smaller models such as TinyLLaMA and retrieval-augmented generation (RAG) models. The models were tested to determine their ability to classify individuals as cognitively normal (CN) or at any stage of Alzheimer's disease (AD). …

    mtu Repository record for EARLY SCREENING OF ALZHEIMER’S DISEASE THROUGH VERBAL COMMUNICATION AND USING LARGE LANGUAGE MODELS (LLMS) (opens in a new tab)

  11. Enhancing the Comprehension: Text Simplification Approaches and the Role of Large Language Models

    … more accessible to patients. Firstly, we assess GPT-3's capacity to generate patient-friendly summaries of radiology sentences, specifically focusing on liver conditions. Our findings reveal that with appropriate prompting and fine-tuning, GPT-3 can produce high-quality simplifications, as …

    temple Repository record for Enhancing the Comprehension: Text Simplification Approaches and the Role of Large Language Models (opens in a new tab)

  12. Constrained, Causal, and Knowledge-Grounded Reasoning for Neural Language Generation

    … Today's language models (LMs, such as GPT-3), despite producing human-like fluent text, essentially act like "a mouth without a brain" -- They generate without grounding on the world knowledge, and lack the ability to flexibly reason about everyday situations and events, including …

    washington Repository record for Constrained, Causal, and Knowledge-Grounded Reasoning for Neural Language Generation (opens in a new tab)

  13. Application of Large Language Models in Code Clone: Benchmarking, Evaluation and Detection

    … the same functionality. As LLMs, like GPT-3, generate code at scale, existing detection tools struggle to handle this complexity, making both syntactic and semantic clone detection more challenging. To address these challenges, our first study introduces GPTCloneBench, a new benchmark …

    sask Repository record for Application of Large Language Models in Code Clone: Benchmarking, Evaluation and Detection (opens in a new tab)

  14. Prompt-tuning in Controlled Dialogue Generation

    … models with billions of parameters like GPT-3. Meanwhile, prompt-tuning has become an increasingly popular parameter-efficient method for steering large pretrained language models to various tasks. Most of the prompting techniques are applied in language understanding and assuming fixed …

    waterloo Repository record for Prompt-tuning in Controlled Dialogue Generation (opens in a new tab)

  15. The artefacts of intelligence: governing scientists' contribution to AI proliferation

    … case study follows: the ‘staged release’ of the GPT-2 language model, where more capable models were gradually released; the platform through which researchers and developers could access GPT-3, the successor to GPT-2; and a wave of new ethics regimes for AI conference publications. The study …

    oxford Repository record for The artefacts of intelligence: governing scientists' contribution to AI proliferation (opens in a new tab)

  16. Shared Context through Multi-Level Attention Transformers for Text Classification

    … Turing NLG is 17billion parameters, and GPT-3 is about 175 billion parameters. Understanding their implications requires the immense computational ability to process the text corpus during both training and inferences. This thesis proposes a novel deep learning architecture for scalable …

    umkc Repository record for Shared Context through Multi-Level Attention Transformers for Text Classification (opens in a new tab)

  17. Introducing controlled reasoning into autoregressive large language models

    … those with a generative pre-trained transformer (GPT) architecture which we categorize into GPT and InstructGPT model types. In both cases, our proposed methods attempt to replicate human cognitive behavior and introduce System 2 (controlled) reasoning into the text generation process. For GPT …

    texas Repository record for Introducing controlled reasoning into autoregressive large language models (opens in a new tab)

  18. Explaining software faults in source code

    … Segundo, utilizando o modelo generativo CodeGPT, abordamos APR como um desafio de code completion, gerando linhas de correção candidatas, com base num ficheiro defeituoso e número de linha, através de um processo de várias etapas que envolve parsing do código, geração de sequências de tokens, …

    minho-thes Repository record for Explaining software faults in source code (opens in a new tab)

  19. Hardware Acceleration of Machine Learning

    … used in various fields, as demonstrated by GPT-3, a large language model that shows impressive performance. However, achieving such excellent performance requires high computational capabilities. Therefore, improving the computational power of current machine learning systems is of great …

    chalmers Repository record for Hardware Acceleration of Machine Learning (opens in a new tab)

  20. Advancing Learnable Neural Network Training Algorithms

    … stably to large-scale unseen tasks such as GPT-3 XL (1.3B) pretraining, which is six orders of magnitude larger than the tasks in its meta-training distribution. We further evaluate Celo2 on GPT-2 (124M) pretraining, ViT ImageNet classification, and Atari reinforcement learning, where it …

    concordia Download PDF for Advancing Learnable Neural Network Training Algorithms (opens in a new tab)

Page 1 of 2