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 8 of 8 for “"Code embeddings"”.

  1. Evaluating Source Code Embeddings from LLMs for Educational Downstream Tasks

    … These techniques extend naturally to source code, which shares similarities with natural language but also exhibits strict syntactic and semantic constraints. This thesis investigates the effectiveness of different source code embedding strategies for three educational tasks: code …

    guelph Repository record for Evaluating Source Code Embeddings from LLMs for Educational Downstream Tasks (opens in a new tab)

  2. Beyond Natural Language Processing: Advancing Software Engineering Tasks through Code Structure

    … between natural language text and source code, researchers have been working on the application of NLP techniques to code-related tasks. However, it is crucial to acknowledge that source code and natural language are different by their natures. For example, source code is highly structured …

    waterloo Repository record for Beyond Natural Language Processing: Advancing Software Engineering Tasks through Code Structure (opens in a new tab)

  3. The limits and promise of software-metric-based prediction: from method-level bugs to app popularity

    … Model (LLM)-based approach for detecting tangled code changes at the method level. By combining commit messages with method-level code diffs, the approach produces cleaner bug labels. Using these datasets, the second study revisits method-level bug prediction across 100 open-source projects, …

    manitoba Repository record for The limits and promise of software-metric-based prediction: from method-level bugs to app popularity (opens in a new tab)

  4. Argus: Detecting Access Control Vulnerabilities in Android Framework using Large Language Models

    … hybrid LLM-driven pipeline that combines static code analysis, code embeddings, and context-aware prompting to improve AC recommendations for Android APIs. Argus begins by extracting path-sensitive summarized program paths from decompiled ROMs and uses rule-based prompting to guide LLMs in …

    waterloo Repository record for Argus: Detecting Access Control Vulnerabilities in Android Framework using Large Language Models (opens in a new tab)

  5. WasmWalker: Path-based Code Representations for Improved WebAssembly Program Analysis

    … enables execution of near-native-performance code in web browsers. Wasm has proven to be useful in applications including gaming, audio and video processing, and cloud computing, providing a high-performance, low-overhead alternative to JavaScript in web development. The fast and widespread …

    waterloo Repository record for WasmWalker: Path-based Code Representations for Improved WebAssembly Program Analysis (opens in a new tab)

  6. Source code representation for comment generation and program comprehension

    Code comment generation is the task of generating a high-level natural language description for a given code snippet. Comments help software developers maintain programs; however, comments are mostly missing or are outdated. Many studies develop models to generate comments automatically, mainly …

    ubc Repository record for Source code representation for comment generation and program comprehension (opens in a new tab) Download PDF for Source code representation for comment generation and program comprehension (opens in a new tab)

  7. Semantic code search using Code2Vec: A bag-of-paths model

    … software is infused with large number of source code files. Therefore, code search has become an intrinsic part of software development process today and the universe of source code is only growing. Although, there are many general purpose search engines such as Google, Bing and other web search …

    waterloo Repository record for Semantic code search using Code2Vec: A bag-of-paths model (opens in a new tab)

  8. Improving Automatic Refactoring Candidate Identification

    … method refactoring is pivotal for enhancing code readability, maintainability, and modularity by segmenting complex code into clearer, isolated methods. Identifying opportunities for such refactorings necessitates a deep understanding of the codebase’s evolution and its intricate …

    rit Repository record for Improving Automatic Refactoring Candidate Identification (opens in a new tab)