Workshop Proceedings Natural language processing (NLP) plays an essential role in several areas of software engineering (SE), and requirements engineering (RE) is no exception. Requirements are generally authored and communicated in textual form and diferent levels of formality, from structured (e.g., user stories) to unstructured natural language. Furthermore, in the last few years, the advent of massive and heterogeneous sources, such as tweets and app reviews, has attracted even more interest from the RE community, and the recent developments in large language models (LLMs) and generative AI have opened new opportunities for RE. LLMs will likely be the enabling technology for solving long-standing RE problems, such as traceability, classification, and compliance.
CEUR ceur-ws.org
RE, poised to redefine the landscape of requirements elicitation, specification, and validation. The presentation was structured into two primary segments. The first part delved into the application of decoder-only models in automating RE tasks. It explored how these models can assist in accurately capturing and specifying requirements, generating requirement documents, and automating the verification of requirements consistency and completeness. By examining case studies and current research, the section highlighted the transformative potential of decoder-only LLMs in enhancing eficiency, accuracy, and comprehensiveness in RE. The second segment of the talk positioned RE as a critical discipline for developing well-crafted prompts essential for interacting with decoder-only LLMs. It underscored the importance of precise, unambiguous, and comprehensive requirements in formulating prompts that elicit accurate and relevant responses from the models. This part also discussed the art and science of crafting efective prompts, drawing parallels between requirements specification techniques and prompt engineering strategies.
We warmly thank all the reviewers of our Program Committee (PC), who helped in the selection of the papers by providing timely and accurate reviews. The PC members of NLP4RE’24 are: • Barbara Paech, University of Heidelberg, Germany • Mehrdad Sabetzadeh, University of Ottawa, Canada • Nicolas Sannier, University of Luxembourg, Luxembourg • Laura Semini, University of Pisa, Italy • Michael Unterkalmsteiner, Blekinge Institute of Technology, Sweden • Han van der Aa, University of Mannheim, Germany • Andreas Vogelsang, University of Cologne, Germany • Liping Zhao, University of Manchester, UK