Collaborative Research: SHF: Medium: Toward Understandability and Interpretability for Neural Language Models of Source Code

合作研究：SHF：媒介：实现源代码神经语言模型的可理解性和可解释性

• 批准号: 2311468
• 负责人: Kevin Moran
• 金额: $ 74.52万
• 依托单位: George Mason University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-10-01 至 2024-04-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2311468&HistoricalAwards=false
• 关键词: Collaborative; Research; SHF; Medium; Toward

Advances in artificial intelligence (AI) have led to the development of several new types of tools for software developers that aim to help automate various parts of the software development process of building and maintaining software. However, the combination of complex underlying deep-learning models and massive training datasets makes it difficult to interpret why these models, and the developer tools powered by them, behave the way they do. Given the increasingly important role that these tools are beginning to play in software engineering (SE), it is imperative that techniques be developed that allow stakeholders to better understand and work with these tools such that critical software infrastructure can be maintained. This project will develop a framework and methodology that enables both researchers who build AI-powered developer tools, and software engineers who use these tools, to interpret why the underlying models make the predictions they do. The objective is to allow researchers to obtain detailed insights into why a model may not be performing as expected, allowing for targeted improvement and informed creation of new models. The methodology will be integrated into AI-powered software development tools, allowing software engineers to make informed decisions about when a tool’s suggestion may be helpful or harmful, thus building trust in their use. The interpretability framework will also enable new forms of interaction with these tools, providing a mechanism for natural language feedback that improves over time. This project will produce and disseminate educational materials on best practices related to building and using AI-powered programming tools. These materials are intended to be integrated into existing computer-literacy courses at all levels of education. In addition, the project will focus on recruiting and retaining computer science students from traditionally underrepresented categories.This project has three specific goals. First, it will design an automated approach for generating global explanations of the behavior of “context-free” neural language models for source code. This component of the project will map predictions from large language models to human-interpretable programming language concepts using causal inference theory, wherein explanations of behavior will be generated via causal interventions. Second, it will develop automated techniques for local explanations of contextualized language models of code by developing a set of interpretability techniques that generate behavioral, feature-based, and textual explanations defined for given SE tasks (e.g., program repair). Finally, the project will create techniques that enable researchers and developers to provide feedback to models based on generated explanations.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

人工智能（AI）的进步已导致为软件开发人员开发了几种新型工具，旨在帮助自动化软件开发过程的各个部分的构建和维护软件。但是，复杂的基础深度学习模型和大规模的培训数据集的结合使得很难解释为什么这些模型以及由它们提供动力的开发人员工具的表现。鉴于这些工具在软件工程（SE）中开始起着越来越重要的作用，因此必须开发出允许利益相关者更好地理解和使用这些工具的技术，以便可以维护关键的软件基础架构。该项目将开发一个框架和方法，使既可以构建AI驱动开发人员工具的研究人员，又可以使用这些工具的软件工程师来解释为什么基础模型为何做出预测。目的是允许研究人员获得详细的见解，了解为什么模型可能不会按预期执行，从而实现有针对性的改进并明智地创建新模型。该方法将被整合到AI驱动的软件开发工具中，使软件工程师可以就何时有助于或有害的建议做出明智的决定，从而建立对其使用的信任。可解释性框架还将实现与这些工具的新形式的互动形式，从而为随着时间的推移提供了一种自然语言反馈的机制。该项目将生产并传播有关与建筑和使用AI驱动的编程工具有关的最佳实践的教育材料。这些材料旨在在各个级别的教育中纳入现有的计算机列表课程中。此外，该项目将着重于传统代表性不足类别的招募和保留计算机科学专业的学生。该项目有三个特定的目标。首先，它将设计一种自动化方法，以生成对源代码“无上下文”中性语言模型行为的全局解释。该项目的这一组成部分将使用催化推理理论绘制从大语言模型到人解剖编程语言概念的预测，其中将通过催化干预措施生成行为的解释。其次，它将通过开发一组可解释性技术来开发自动化的技术，以解释代码的本地解释，这些技术产生了针对给定的SE任务定义的行为，基于功能的和纹理说明（例如，程序修复）。最后，该项目将创建技术，使研究人员和开发人员能够根据生成的解释提供对模型的反馈。该奖项反映了NSF的法定使命，并使用基金会的知识分子优点和更广泛的影响评估审查标准，被认为是珍贵的支持。