Characterising the Quality of Behaviour Driven Development Specifications

Binamungu, Leonard Peter; Embury, Suzanne M.; Κωνσταντίνου, Νικόλαος

doi:10.1007/978-3-030-49392-9_6

Cited by 8 publications

(2 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ensuring highquality BDD acceptance tests is crucial for successful implementation [34]. The term "high-quality BDD acceptance tests" denotes adherence to Gherkin rules and best practices outlined in the methodology section [6]. In addition, significant experience is required to craft good quality BDD acceptance tests.…”

Section: Scenario: Performing Additionmentioning

confidence: 99%

Comprehensive Evaluation and Insights Into the Use of Large Language Models in the Automation of Behavior-Driven Development Acceptance Test Formulation

Karpurapu,

Myneni,

Nettur

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Behavior-driven development (BDD) is an Agile testing methodology fostering collaboration among developers, QA analysts, and stakeholders. In this manuscript, we propose a novel approach to enhance BDD practices using large language models (LLMs) to automate acceptance test generation. Our study uses zero and few-shot prompts to evaluate LLMs such as GPT-3.5, GPT-4, Llama-2-13B, and PaLM-2. The paper presents a detailed methodology that includes the dataset, prompt techniques, LLMs, and the evaluation process. The results demonstrate that GPT-3.5 and GPT-4 generate error-free BDD acceptance tests with better performance. The few-shot prompt technique highlights its ability to provide higher accuracy by incorporating examples for in-context learning. Furthermore, the study examines syntax errors, validation accuracy, and comparative analysis of LLMs, revealing their effectiveness in enhancing BDD practices. However, our study acknowledges that there are limitations to the proposed approach. We emphasize that this approach can support collaborative BDD processes and create opportunities for future research into automated BDD acceptance test generation using LLMs.INDEX TERMS agile software development, behavior driven development, large language model, machine learning, natural language processing, prompt engineering, software testing, test cases, test automation, zero-shot, few-shot.

show abstract

Section: Scenario: Performing Additionmentioning

confidence: 99%

Comprehensive Evaluation and Insights Into the Use of Large Language Models in the Automation of Behavior-Driven Development Acceptance Test Formulation

Karpurapu,

Myneni,

Nettur

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…We therefore make certain assumptions about the use of the BDD scenario template shown in Table 1. These assumptions were inspired by good quality principles for BDD scenarios [38].…”

Section: Given [Context] And/or [Some More Context] When [Some Event ...mentioning

confidence: 99%

Generating multiple conceptual models from behavior-driven development scenarios

Gupta

Poels

Bera

2023

Data & Knowledge Engineering

View full text Add to dashboard Cite

Investigating Quality Attributes in Behavior-Driven Development Scenarios: An Evaluation Framework and an Experimental Supporting Tool

Wautelet,

Nassiri,

Tsilionis

2023

Lecture Notes in Business Information Processing

View full text Add to dashboard Cite

Characterising the Quality of Behaviour Driven Development Specifications

Cited by 8 publications

References 15 publications

Comprehensive Evaluation and Insights Into the Use of Large Language Models in the Automation of Behavior-Driven Development Acceptance Test Formulation

Comprehensive Evaluation and Insights Into the Use of Large Language Models in the Automation of Behavior-Driven Development Acceptance Test Formulation

Generating multiple conceptual models from behavior-driven development scenarios

Investigating Quality Attributes in Behavior-Driven Development Scenarios: An Evaluation Framework and an Experimental Supporting Tool

Contact Info

Product

Resources

About