Code Comparison Tuning for Code Large Language Models
원문 초록
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 containing manually added code errors, we use token-level preference loss for detailed token-level comparisons. Additionally, we combine code segments to create a new instruction tuning sample for sequence-level comparisons, enhancing the model's bug-fixing capability. Experimental results on the HumanEvalFix benchmark show that CCT surpasses instruction tuning in pass@1 scores by up to 4 points across diverse code LLMs, and extensive analysis demonstrates the effectiveness of our method.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
CoreCodeBench: A Configurable Multi-Scenario Repository-Level Benchmark
SWE-Dev: Evaluating and Training Autonomous Feature-Driven Software Development
Less is More: Adaptive Program Repair with Bug Localization and Preference Learning
Repository-level Code Search with Neural Retrieval Methods
GREEN-CODE: Learning to Optimize Energy Efficiency in LLM-based Code Generation
CoRNStack: High-Quality Contrastive Data for Better Code Retrieval and Reranking
토론
이 논문과 연결된 포럼 글이 아직 없습니다.