JWJules White

Jules White

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Jules White has a total of 33 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Prompt Engineering for Structured Data A Comparative Evaluation of Styles and LLM Performance

    by Jules White, Ashraf Elnashar, Douglas Schmidt

    The effectiveness of prompt engineering strategies for structured data generation remains an open challenge, especially as the capabilities and architectures of large language models (LLMs) continue to evolve. While prior research has examined a limited set of prompt styles using GPT-4o [8], this study expands the scope significantly by comparing six prompt styles—JSON, YAML, CSV, function calling APIs, simple prefixes, and a hybrid CSV/prefix format—across three state-of-the-art LLMs: ChatGPT-4o, Claude, and Gemini. Building upon our earlier findings, which focused on evaluating three prompt styles within GPT-4o, this study introduces a broader prompt set and performs a comparative analysis across multiple models to generalize and extend prior conclusions. These datasets are used to evaluate each prompt style for these LLMs across three critical metrics: accuracy in reproducing the expected data attributes, token cost for API usage, and time needed to generate data. Our methodology incorporates structured data validation and analysis through Python utilities that ensure precise comparison and document each style’s performance. We visualize the results via Technique vs. Accuracy, Technique vs. Token Cost, and Technique vs. Time graphs. Our results reveal trade-offs between prompt complexity and performance, suggesting that simpler formats may provide efficiency benefits with minimal loss in accuracy, while more flexible formats offer enhanced versatility for handling complex data structures. Our extended findings demonstrate that prompt selection substantially affects both quality and resource efficiency. Claude consistently yields the highest accuracy, ChatGPT-4o is the most token- and time-efficient, and Gemini offers a balanced trade-off across metrics. These results extend earlier single-model evaluations and provide practical guidelines for choosing prompt styles based on model capabilities and application-specific constraints. This work advances the field of prompt engineering by offering a comprehensive, multi-model framework for optimizing structured data generation.


  • Open Access

    Building Living Software Systems with Generative & Agentic AI

    by Jules White

    This paper is an opinion paper that looks at the future of computing in the age of Generative \& Agentic AI. Current software systems are static and inflexible, leading to significant challenges in translating human goals into computational actions. "Living software systems" powered by generative AI offer a solution to this fundamental problem in computing. Traditional software development involves multiple layers of imperfect translation, from business requirements to code, resulting in rigid systems that struggle to adapt to changing user needs and contexts. Generative AI, particularly large language models, can serve as a universal translator between human intent and computer operations. This approach enables the creation of more flexible, context-aware systems that can dynamically evolve to meet user goals. Two pathways for implementing living software systems are explored: using generative AI to accelerate traditional software development, and leveraging agentic AI to create truly adaptive systems. New skills like Prompt Engineering are necessary. By reimagining software as a living, adaptable entity, we can create computing interfaces that are more intuitive, powerful, and responsive to human needs.


  • Top Cited Papers

    ChatGPT Prompt Patterns for Improving Code Quality, Refactoring, Requirements Elicitation, and Software Design

    by Jules White, Sam Hays, Quchen Fu, Jesse Spencer-Smith, Douglas C. Schmidt


  • Open Access

    Using LLMs for Tabletop Exercises within the Security Domain

    by Sam Hays, Jules White

    Tabletop exercises are a crucial component of many company's strategy to test and evaluate its preparedness for security incidents in a realistic way. Traditionally led by external firms specializing in cybersecurity, these exercises can be costly, time-consuming, and may not always align precisely with the client's specific needs. Large Language Models (LLMs) like ChatGPT offer a compelling alternative. They enable faster iteration, provide rich and adaptable simulations, and offer infinite patience in handling feedback and recommendations. This approach can enhances the efficiency and relevance of security preparedness exercises.

  • Open Access

    Employing LLMs for Incident Response Planning and Review

    by Sam Hays, Jules White

    Incident Response Planning (IRP) is essential for effective cybersecurity management, requiring detailed documentation (or playbooks) to guide security personnel during incidents. Yet, creating comprehensive IRPs is often hindered by challenges such as complex systems, high turnover rates, and legacy technologies lacking documentation. This paper argues that, despite these obstacles, the development, review, and refinement of IRPs can be significantly enhanced through the utilization of Large Language Models (LLMs) like ChatGPT. By leveraging LLMs for tasks such as drafting initial plans, suggesting best practices, and identifying documentation gaps, organizations can overcome resource constraints and improve their readiness for cybersecurity incidents. We discuss the potential of LLMs to streamline IRP processes, while also considering the limitations and the need for human oversight in ensuring the accuracy and relevance of generated content. Our findings contribute to the cybersecurity field by demonstrating a novel approach to enhancing IRP with AI technologies, offering practical insights for organizations seeking to bolster their incident response capabilities.


  • Open Access

    Reducing Usefulness of Stolen Credentials in SSO Contexts

    by Sam Hays, Michael Sandborn, Jules White

    Approximately 61% of cyber attacks involve adversaries in possession of valid credentials. Attackers acquire credentials through various means, including phishing, dark web data drops, password reuse, etc. Multi-factor authentication (MFA) helps to thwart attacks that use valid credentials, but attackers still commonly breach systems by tricking users into accepting MFA step up requests through techniques, such as ``MFA Bombing'', where multiple requests are sent to a user until they accept one. Currently, there are several solutions to this problem, each with varying levels of security and increasing invasiveness on user devices. This paper proposes a token-based enrollment architecture that is less invasive to user devices than mobile device management, but still offers strong protection against use of stolen credentials and MFA attacks.


  • Open Access

    NL2CMD: An Updated Workflow for Natural Language to Bash Commands Translation

    by Quchen Fu, Zhongwei Teng, Marco Georgaklis, Jules White, Douglas C. Schmidt

    Translating natural language into Bash Commands is an emerging research field that has gained attention in recent years. Most efforts have focused on producing more accurate translation models. To the best of our knowledge, only two datasets are available, with one based on the other. Both datasets involve scraping through known data sources (through platforms like stack overflow, crowdsourcing, etc.) and hiring experts to validate and correct either the English text or Bash Commands. This paper provides two contributions to research on synthesizing Bash Commands from scratch. First, we describe a state-of-the-art translation model used to generate Bash Commands from the corresponding English text. Second, we introduce a new NL2CMD dataset that is automatically generated, involves minimal human intervention, and is over six times larger than prior datasets. Since the generation pipeline does not rely on existing Bash Commands, the distribution and types of commands can be custom adjusted. We evaluate the performance of ChatGPT on this task and discuss the potential of using it as a data generator. Our empirical results show how the scale and diversity of our dataset can offer unique opportunities for semantic parsing researchers.


  • Open Access

    Semantic Compression With Large Language Models

    by Henry Gilbert, Michael Sandborn, Douglas C. Schmidt, Jesse Spencer-Smith, Jules White

    The rise of large language models (LLMs) is revolutionizing information retrieval, question answering, summarization, and code generation tasks. However, in addition to confidently presenting factually inaccurate information at times (known as "hallucinations"), LLMs are also inherently limited by the number of input and output tokens that can be processed at once, making them potentially less effective on tasks that require processing a large set or continuous stream of information. A common approach to reducing the size of data is through lossless or lossy compression. Yet, in some cases it may not be strictly necessary to perfectly recover every detail from the original data, as long as a requisite level of semantic precision or intent is conveyed. This paper presents three contributions to research on LLMs. First, we present the results from experiments exploring the viability of approximate compression using LLMs, focusing specifically on GPT-3.5 and GPT-4 via ChatGPT interfaces. Second, we investigate and quantify the capability of LLMs to compress text and code, as well as to recall and manipulate compressed representations of prompts. Third, we present two novel metrics -- Exact Reconstructive Effectiveness (ERE) and Semantic Reconstruction Effectiveness (SRE) -- that quantify the level of preserved intent between text compressed and decompressed by the LLMs we studied. Our initial results indicate that GPT-4 can effectively compress and reconstruct text while preserving the semantic essence of the original text, providing a path to leverage $\sim$5$\times$ more tokens than present limits allow.


  • Open Access

    ChatGPT Prompt Patterns for Improving Code Quality, Refactoring, Requirements Elicitation, and Software Design

    by Jules White, Sam Hays, Quchen Fu, Jesse Spencer-Smith, Douglas C. Schmidt

    This paper presents prompt design techniques for software engineering, in the form of patterns, to solve common problems when using large language models (LLMs), such as ChatGPT to automate common software engineering activities, such as ensuring code is decoupled from third-party libraries and simulating a web application API before it is implemented. This paper provides two contributions to research on using LLMs for software engineering. First, it provides a catalog of patterns for software engineering that classifies patterns according to the types of problems they solve. Second, it explores several prompt patterns that have been applied to improve requirements elicitation, rapid prototyping, code quality, refactoring, and system design.


  • Top Cited Papers
    Open Access

    A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT

    by Jules White, Quchen Fu, Sam Hays, Michael Sandborn, Carlos Olea, Henry Gilbert, Ashraf Elnashar, Jesse Spencer-Smith, Douglas C. Schmidt

    Prompt engineering is an increasingly important skill set needed to converse effectively with large language models (LLMs), such as ChatGPT. Prompts are instructions given to an LLM to enforce rules, automate processes, and ensure specific qualities (and quantities) of generated output. Prompts are also a form of programming that can customize the outputs and interactions with an LLM. This paper describes a catalog of prompt engineering techniques presented in pattern form that have been applied to solve common problems when conversing with LLMs. Prompt patterns are a knowledge transfer method analogous to software patterns since they provide reusable solutions to common problems faced in a particular context, i.e., output generation and interaction when working with LLMs. This paper provides the following contributions to research on prompt engineering that apply LLMs to automate software development tasks. First, it provides a framework for documenting patterns for structuring prompts to solve a range of problems so that they can be adapted to different domains. Second, it presents a catalog of patterns that have been applied successfully to improve the outputs of LLM conversations. Third, it explains how prompts can be built from multiple patterns and illustrates prompt patterns that benefit from combination with other prompt patterns.