首页/论文/2001.09925

arXiv 2001.099252020-01-27cs.SEcs.HC

The Apiza Corpus: API Usage Dialogues with a Simulated Virtual Assistant

Zachary Eberhart, Aakash Bansal, Collin McMillan

备注：: Preview of an upcoming TSE submission. 3 Pages + references. The Apiza corpus and relevant data can be found at https://github.com/ApizaCorpus/ApizaCorpus

英文摘要：

Virtual assistant technology has the potential to make a significant impact in the field of software engineering. However, few SE-related datasets exist that would be suitable for the design or training of a virtual assistant. To help lay the groundwork for a hypothetical virtual assistant for API usage, we designed and conducted a Wizard-of-Oz study to gather this crucial data. We hired 30 professional programmers to complete a series of programming tasks by interacting with a simulated virtual assistant. Unbeknownst to the programmers, the virtual assistant was actually operated by another human expert. In this report, we describe our experimental methodology and summarize the results of the study.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

A Wizard of Oz Study Simulating API Usage Dialogues with a Virtual Assistant

Virtual Assistant technology is rapidly proliferating to improve productivity in a variety of tasks. While several virtual assistants for everyday tasks are well-known (e.g., Siri, Cortana, Alexa), assistants for specialty tasks such as software engineering are rarer. One key reason software engineering assistants are rare is that very few experimental datasets are available and suitable for training the AI that is the bedrock of current virtual assistants. In this paper, we present a set of Wizard of Oz experiments that we designed to build a dataset for creating a virtual assistant. Our targ…

2021-06-23cs.HCcs.SE

Dialogue Management for Interactive API Search

API search involves finding components in an API that are relevant to a programming task. For example, a programmer may need a function in a C library that opens a new network connection, then another function that sends data across that connection. Unfortunately, programmers often have trouble finding the API components that they need. A strong scientific consensus is emerging towards developing interactive tool support that responds to conversational feedback, emulating the experience of asking a fellow human programmer for help. A major barrier to creating these interactive tools is impleme…

2021-07-26cs.HCcs.SE

APIDA-Chat：结构化合成 API 搜索对话以引导会话智能体

APIDA-Chat: Structured Synthesis of API Search Dialogues to Bootstrap Conversational Agents

针对小众 API 多轮对话数据稀缺问题，本文提出 APIDA-Chat 流水线，通过教师模型生成黄金对话并蒸馏微调 Llama 3.2 3B，实现低成本、本地化的 API 搜索对话合成。

2025-10-04cs.SE

理解人工智能代码助手对安全API使用的影响：一项实证研究

Understanding the Impact of AI Code Assistants on Security API Usage: An Empirical Study

Centre for Research on Engineering Software Technologies (CREST) & Adelaide University, Australia（工程软件研究技术中心（CREST）及阿德莱德大学，澳大利亚）；Edith Cowan University, Australia（埃德温·考文大学，澳大利亚）；CSIRO’s Data61, Australia（CSIRO数据61，澳大利亚）

该研究通过对44名开发者的实证调查，探讨人工智能代码助手对安全API使用的影响。发现GitHub Copilot虽提高功能正确性、减少不安全模式，但未显著提升安全API使用，且开发者安全意识不足，进而给出相关建议与研究方向。

2026-07-14cs.AIcs.SE

回答不确定、欠指定的 API 查询：借助知识感知的人机对话

Answering Uncertain, Under-Specified API Queries Assisted by Knowledge-Aware Human-AI Dialogue

本文提出知识感知人机对话代理 KAHAID，通过多轮问答澄清不确定的 API 查询，提供可解释和可扩展的推荐，显著提升推荐效果与用户启发。

2023-04-27cs.SE

APITestGenie：通过生成式AI实现自动化API测试生成

APITestGenie: Automated API Test Generation through Generative AI

针对Web API测试难题，本文提出APITestGenie，利用LLM依据业务需求和API规范生成可执行测试脚本，并在真实API实验中验证其有效性。

2024-09-05cs.SE

更多相关论文收起更多论文

A Survey on Artificial Intelligence for Source Code: A Dialogue Systems Perspective

University of North Carolina at Charlotte（北卡罗来纳大学夏洛特分校）

In this survey paper, we overview major deep learning methods used in Natural Language Processing (NLP) and source code over the last 35 years. Next, we present a survey of the applications of Artificial Intelligence (AI) for source code, also known as Code Intelligence (CI) and Programming Language Processing (PLP). We survey over 287 publications and present a software-engineering centered taxonomy for CI placing each of the works into one category describing how it best assists the software development cycle. Then, we overview the field of conversational assistants and their applications in…

2022-02-10cs.CLcs.CYcs.LG

车载对话助手中多轮对话的自动化评估

Automated Evaluation of Multi-Turn Dialogues in In-Car Conversational Assistants

Friedrich-Alexander-Universität Erlangen-Nürnberg（埃尔朗根-纽伦堡弗里德里希-亚历山大大学）；BMW Group（宝马集团）；Technical University of Munich（慕尼黑工业大学）；RWTH Aachen University（亚琛工业大学）；fortiss GmbH（fortiss有限公司）

针对车载对话助手多轮交互评估难题，提出基于策略引导用户模拟器与双层LLM评判器的自动化框架，显著提升失败类型与失败对话的发现效率。

2026-09-30cs.CLcs.SE

Conv-to-Bench: 通过代码任务中的用户-助手对话评估语言模型

Conv-to-Bench: Evaluating Language Models Via User-Assistant Dialogues In Code Tasks

Institute of Mathematics and Computer Science, University of São Paulo（圣保罗大学数学与计算机科学学院）；Institute of Informatics, Federal University of Goiás（戈亚斯联邦大学信息学院）；HUG Labs（HUG实验室）；Advanced Knowledge Center for Immersive Technologies (AKCIT)（沉浸式技术高级知识中心）

提出Conv-to-Bench框架，自动将多轮用户-助手对话转化为结构化需求清单，用于评估大语言模型，在编程领域与人工标准高度一致且计算开销低。

2026-04-07cs.CLcs.SE

我们能信任 AI 结对程序员吗？Copilot 在 API 误用检测与纠正中的应用

Can We Trust the AI Pair Programmer? Copilot for API Misuse Detection and Correction

本研究利用 MUBench 基准评估 GitHub Copilot 在 API 误用检测与纠正中的表现，发现其检测准确率达 86.2% 且能修复超过 95% 的已识别误用，验证了 AI 结对编程的可行性。

2025-09-20cs.SE

CodeScholar：生成地道代码示例

CodeScholar: Growing Idiomatic Code Examples

CodeScholar通过神经引导图搜索生成地道API使用示例，用户偏好度达70%，优于GPT3.5，且生成更逼真、多样、简洁的代码，并辅助LLM编程助手。

2023-12-23cs.LGcs.PLcs.SE