LLMs automate requirement dependency detection with high accuracy

Researchers have developed LEREDD, a novel approach that utilizes large language models (LLMs) to automate the detection of requirement dependencies in software development. This method employs Retrieval-Augmented Generation (RAG) and In-Context Learning (ICL) to identify these crucial interconnections within natural language requirements, a task often overlooked due to its complexity and manual effort. LEREDD demonstrates significant improvements over existing methods, achieving an accuracy of 0.93 and an F1 score of 0.84, with notable gains in identifying fine-grained dependency types. AI

IMPACT Enhances software development efficiency by automating a complex, manual task in requirements engineering.

RANK_REASON The cluster contains a research paper detailing a new method for requirement dependency detection using LLMs. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• arXiv
• In-Context Learning
• Hugging Face
• Ikram Darif
• large-language models
• natural language
• retrieval-augmented generation

• paper
• product
• infra

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →