Online Appendix: A Retrieval Augmented Generation Architecture for Automated Glossary Compliance in Requirement Engineering
Abstract
This is the supplementari material for the paper "A Retrieval Augmented Generation Architecture for Automated Glossary Compliance in Requirement Engineering". Specifically, It contains the following files: nasa-test-data.json: Annotated requirements from the NASA dataset used to evaluate the effectiveness of the R4 rule implementation; gamma-j-test-data.json: Annotated requirements from the Gamma J dataset used to evaluate the effectiveness of the R4 rule implementation; nist-test-data.json: Annotated requirements from the NIST dataset used to evaluate the effectiveness of the R4 rule implementation; r4_few_shots.json: Few-shot examples used to instruct the LLM on how to identify the violations to INCOSE Rules 4 within the requirement formulation; judge_characteristics.json: The definition of the 5 ISO/IEC/IEE 29148 quality characteristics evaluated by the judge, and a collection of few-shot examples for each charachteristic, to ground the responses from the judge; prompts.md: System prompts used for: the extract violations of R4, the automatic elicitation process in 'DeepElicit', and the judge evaluation; examples.zip: It contains two examples of a manual requirement elicitation process in 'DeepElicit', and the comparison in length of three requirement that went through the automatic elicitation process during the benchmarks; nasa_glossary.csv: Collection of terms and definition extracted from the NASA document contained in the PURE dataset. gamma-j-glossary.csv: Collection…
Read the paper
Related studies
- Knowledge Management Perspective of Generative Artificial Intelligence
- Navigating Generative Artificial Intelligence Promises and Perils for Knowledge and Creative Work
- Characterizing the evolving research on enterprise content management
- Large language models and multimodal foundation models for precision oncology
- From Generative AI to Extended Reality: Multidisciplinary Perspectives on the Challenges, Opportunities, and Future of Educational Computing
- Generative Artificial Intelligence: A New Engine for Advancing Environmental Science and Engineering
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.