
The core message of this paper is to introduce a novel retrieval-augmented method called FT2Ra, which aims to mimic the effects of genuine fine-tuning without the need for actual fine-tuning. FT2Ra is designed to effectively leverage the Δlogits information from retrieved neighbors to enhance the predictions of pre-trained code models.


coremsg

ft2ra-a-fine-tuning-inspired-approach-to-retrieval-augmented-code-completion


FT2Ra: A Fine-Tuning-Inspired Approach to Retrieval-Augmented Code Completion


title_rewrite


Efficient code completion through selective retrieval with REPOFORMER.


selective-retrieval-for-efficient-code-completion-repoformer


Selective Retrieval for Efficient Code Completion: REPOFORMER
