Replication Package for: Understanding LLM-Driven Test Oracle Generation - AIWare 2025
收藏Figshare2025-10-29 更新2026-04-08 收录
下载链接：
https://figshare.com/articles/dataset/Replication_Package_for_Understanding_LLM-Driven_Test_Oracle_Generation_-_AIWare_2025/30472256/1
下载链接
链接失效反馈官方服务：
资源简介：
Understanding LLM-Driven Test Oracle GenerationAuthors: Adam Bodicoat, Gunel Jahangirova, Valerio TerragniAIware 2025 – 2nd ACM International Conference on AI-powered Software(19–20 Nov 2025, Seoul, South Korea – co-located with ASE 2025)Paper available here: https://valerio-terragni.github.io/assets/pdf/bodicoat-aiware-2025.pdfWe explore how Large Language Models (LLMs) can automatically generate <b>t</b>est oracles, the components of software tests that decide whether a program’s behavior is correct. We evaluate different prompting strategies and levels of contextual input to understand how they affect the quality and reliability of the generated oracles. Our study shows that LLMs can effectively help detect software failures and reduce manual testing effort, though their success heavily depends on prompt design and the context provided.<br>
提供机构：
Jahangirova, Gunel; Terragni, Valerio; Bodicoat, Adam
创建时间：
2025-10-29
