DolphCoder: Echo-Locating Code Large Language Models with Diverse and Multi-Objective Instruction Tuning

arXiv:2402.09136v1 Announce Type: new
Abstract: Code Large Language Models (Code LLMs) have demonstrated outstanding performance in code-related tasks. Several instruction tuning approaches have been proposed to boost the code generation performance of pre-trained Code LLMs. In this paper, we introduce a diverse instruction model (DolphCoder) with self-evaluating for code generation. It learns diverse instruction targets and combines a code evaluation objective to enhance its code generation ability. Our model achieves superior performance on the HumanEval and MBPP benchmarks, demonstrating new …

abstract arxiv boost code code generation code llms cs.ai cs.cl diverse echo language language models large language large language models llms multi-objective paper performance tasks type