← all papers · overview

Code Comparison Tuning For Code Large Language Models

Abstract

We present Code Comparison Tuning (CCT), a simple and effective tuning method for code large language models (Code LLMs) to better handle subtle code errors. Specifically, we integrate the concept of comparison into instruction tuning, both at the token and sequence levels, enabling the model to discern even the slightest deviations in code. To compare the original code with an erroneous version c

Related papers

Ranked by semantic similarity — how closely each paper's abstract matches this one (100% = near-identical topic).