Dense retrieval combined with traditional machine learning rerankers outperforms both sparse methods and LLM-based reranking for recovering issue-commit links in software projects.
Title resolution pending
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
-
Think Harder and Don't Overlook Your Options: Revisiting Issue-Commit Linking with LLM-Assisted Retrieval
Dense retrieval combined with traditional machine learning rerankers outperforms both sparse methods and LLM-based reranking for recovering issue-commit links in software projects.