TraceLLM uses prompt engineering and label-aware demonstration selection with eight LLMs on four benchmark datasets to achieve state-of-the-art F2 scores for requirements traceability, outperforming IR baselines and prior LLM methods.
Automated techniques for capturing custom traceabil- ity links across heterogeneous artifacts
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
TraceLLM: Leveraging Large Language Models with Prompt Engineering for Enhanced Requirements Traceability
TraceLLM uses prompt engineering and label-aware demonstration selection with eight LLMs on four benchmark datasets to achieve state-of-the-art F2 scores for requirements traceability, outperforming IR baselines and prior LLM methods.