Towards Human-Bot Collaborative Software Architecting with ChatGPT

Ahmad, Aakash; Waseem, Muhammad; Peng, Liang; Fehmideh, Mahdi; Aktar, Mst Shamima; Mikkonen, Tommi

doi:10.48550/arxiv.2302.14600

Cited by 3 publications

(1 citation statement)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…NLP's growing relevance in requirements engineering and the generation of SysML diagrams from unstructured text is also noted [6]. Standardized methods in NLP integration within agile development are called for [7,8].…”

Section: Advancements and Applications Of Nlpmentioning

confidence: 99%

Gunning Fog Index and Automated UML Generation

Djaber,

HADJADJ

2023

Preprint

View full text Add to dashboard Cite

This research investigates the influence of the Gunning Fog Index (GFI) on the production of PlantUML use case diagrams by ChatGPT, within the context of software development projects, particularly focusing on E-commerce for Special Shoes. The study emphasizes the impact of linguistic complexity, as measured by GFI, on the automated code-generation process. It reveals that lower GFI scores, indicative of clearer text, lead to more easily comprehensible code representations, while higher scores correlate with intricate but potentially less accessible code artifacts. This reflects a nuanced balance between detail and clarity in the specifications. A key finding is the significant contribution of integrating linguistic clarity met-rics like GFI into the code generation workflow. This integration is shown to enhance code quality, usability, and facilitate collaboration among stakeholders. Despite the study’s focus on GFI to the exclusion of other readability metrics, it provides valuable insights into the role of linguistic complexity in shaping software artifacts generated by ChatGPT. Recognizing the importance of readability allows developers to more effectively translate natural language specifications into machine-generated code, yielding benefits in diverse project scenarios.

show abstract

Section: Advancements and Applications Of Nlpmentioning

confidence: 99%

Gunning Fog Index and Automated UML Generation

Djaber,

HADJADJ

2023

Preprint

View full text Add to dashboard Cite

show abstract

AI-Powered Chatbots and the Transformation of Work: Findings from a Case Study in Software Development and Software Engineering

Süße,

Kobert,

Grapenthin

et al. 2023

IFIP Advances in Information and Communication Technology

View full text Add to dashboard Cite

VeriGen: A Large Language Model for Verilog Code Generation

Thakur,

Ahmad,

Pearce

et al. 2024

ACM Trans. Des. Autom. Electron. Syst.

View full text Add to dashboard Cite

In this study, we explore the capability of Large Language Models (LLMs) to automate hardware design by automatically completing partial Verilog code, a common language for designing and modeling digital systems. We fine-tune pre-existing LLMs on Verilog datasets compiled from GitHub and Verilog textbooks. We evaluate the functional correctness of the generated Verilog code using a specially designed test suite, featuring a custom problem set and testing benches. Here, our fine-tuned open-source CodeGen-16B model outperforms the commercial state-of-the-art GPT-3.5-turbo model with a 1.1% overall increase. Upon testing with a more diverse and complex problem set, we find that the fine-tuned model shows competitive performance against state-of-the-art gpt-3.5-turbo, excelling in certain scenarios. Notably, it demonstrates a 41% improvement in generating syntactically correct Verilog code across various problem categories compared to its pre-trained counterpart, highlighting the potential of smaller, in-house LLMs in hardware design automation. We release our training/evaluation scripts and LLM checkpoints as open-source contributions.

show abstract

Towards Human-Bot Collaborative Software Architecting with ChatGPT

Cited by 3 publications

References 14 publications

Gunning Fog Index and Automated UML Generation

Gunning Fog Index and Automated UML Generation

AI-Powered Chatbots and the Transformation of Work: Findings from a Case Study in Software Development and Software Engineering

VeriGen: A Large Language Model for Verilog Code Generation

Contact Info

Product

Resources

About