Federated cumulative fine-tuning of LLaMA-3 with a separate classifier is the best multi-task setup for code review automation, but gains are small and sequential training causes catastrophic forgetting.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Code Review Automation Via Multi-task Federated LLM -- An Empirical Study
Federated cumulative fine-tuning of LLaMA-3 with a separate classifier is the best multi-task setup for code review automation, but gains are small and sequential training causes catastrophic forgetting.