LLMs automate alignment of interview transcripts to software requirements

Researchers have developed a method to automatically align interview transcripts with software requirements, represented as user stories. They introduced two metrics: "requirements faithfulness" and "interview coverage." Experiments using large language models demonstrated an 0.86 macro-F1 score on labeled data, suggesting LLMs can effectively evaluate these metrics. This work aims to streamline the process of tracing conversational artifacts to requirements and potentially generate requirements from conversations. AI

IMPACT Automates a key step in software development, potentially speeding up requirement gathering and reducing errors.

RANK_REASON The cluster contains an academic paper detailing a new methodology and experimental results for a specific NLP task. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CL →

• Francesco Dente
• Large Language Models

• paper
• product

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