A retrieval-augmented LLM approach validates and recovers traceability links between stakeholder and system requirements for automotive diagnostic trouble codes, reporting 98.87% validation accuracy and 85.50% recovery correctness on industrial data.
In: International Working Conference on Requirements Engineering: Foundation for Software Quality, pp
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
TVR: Automotive System Requirement Traceability Validation and Recovery Through Retrieval-Augmented Generation
A retrieval-augmented LLM approach validates and recovers traceability links between stakeholder and system requirements for automotive diagnostic trouble codes, reporting 98.87% validation accuracy and 85.50% recovery correctness on industrial data.