LiSSA: Toward Generic Traceability Link Recovery through Retrieval-Augmented Generation
This program is tentative and subject to change.
There are a multitude of software artifacts which need to be handled during the development and maintenance of a software system. These artifacts interrelate in multiple, complex ways. Therefore, many software engineering tasks are enabled — and even empowered — by a clear understanding of artifact interrelationships and also by the continued advancement of techniques for automated artifact linking.
However, current approaches in automatic Traceability Link Recovery (TLR) target mostly the links between specific sets of artifacts, such as those between requirements and code. Fortunately, recent advancements in Large Language Models (LLMs) can enable TLR approaches to achieve broad applicability. Still, it is a nontrivial problem how to provide the LLMs with the specific information needed to perform TLR.
In this paper, we present LiSSA, a framework that harnesses LLM performance and enhances them through Retrieval-Augmented Generation (RAG). We empirically evaluate LiSSA on three different TLR tasks, requirements to code, documentation to code, and architecture documentation to architecture models, and we compare our approach to state-of-the-art approaches.
Our results show that the RAG-based approach can significantly outperform the state-of-the-art on the code-related tasks. However, further research is required to improve the performance of RAG-based approaches to be applicable in practice.
This program is tentative and subject to change.
Thu 1 MayDisplayed time zone: Eastern Time (US & Canada) change
11:00 - 12:30 | AI for RequirementsResearch Track / SE In Practice (SEIP) / Journal-first Papers / New Ideas and Emerging Results (NIER) at 213 | ||
11:00 15mTalk | From Bugs to Benefits: Improving User Stories by Leveraging Crowd Knowledge with CrUISE-AC Research Track | ||
11:15 15mTalk | LiSSA: Toward Generic Traceability Link Recovery through Retrieval-Augmented Generation Research Track Dominik Fuchß Karlsruhe Institute of Technology (KIT), Tobias Hey Karlsruhe Institute of Technology (KIT), Jan Keim Karlsruhe Institute of Technology (KIT), Haoyu Liu Karlsruhe Institute of Technology (KIT), Niklas Ewald Karlsruhe Institute of Technology (KIT), Tobias Thirolf Karlsruhe Institute of Technology (KIT), Anne Koziolek Karlsruhe Institute of Technology Pre-print | ||
11:30 15mTalk | Replication in Requirements Engineering: the NLP for RE Case Journal-first Papers Sallam Abualhaija University of Luxembourg, Fatma Başak Aydemir Utrecht University, Fabiano Dalpiaz Utrecht University, Davide Dell'Anna Utrecht University, Alessio Ferrari CNR-ISTI, Xavier Franch Universitat Politècnica de Catalunya, Davide Fucci Blekinge Institute of Technology | ||
11:45 15mTalk | On the Impact of Requirements Smells in Prompts: The Case of Automated Traceability New Ideas and Emerging Results (NIER) Andreas Vogelsang University of Cologne, Alexander Korn University of Cologne, Giovanna Broccia ISTI-CNR, FMT Lab, Alessio Ferrari Consiglio Nazionale delle Ricerche (CNR) and University College Dublin (UCD), Jannik Fischbach Netlight Consulting GmbH and fortiss GmbH, Chetan Arora Monash University | ||
12:00 15mTalk | NICE: Non-Functional Requirements Identification, Classification, and Explanation Using Small Language Models SE In Practice (SEIP) |