WarriorCoder: Learning from Expert Battles to Augment Code Large Language Models
원문 초록
Despite recent progress achieved by code large language models (LLMs), their remarkable abilities are largely dependent on fine-tuning on the high-quality data, posing challenges for data collection and annotation. To address this, current methods often design various data flywheels to gather complex code instructions, enabling models to handle more intricate tasks. However, these approaches typically rely on off-the-shelf datasets and data augmentation from the limited pool of proprietary LLMs (e.g., Claude, GPT4, and so on), which limits the diversity of the constructed data and makes it prone to systemic biases. In this paper, we propose WarriorCoder which learns from expert battles to address these limitations. Specifically, we create an arena for current expert code LLMs, where each model challenges and responds to others' challenges, with evaluations conducted by uninvolved judge models. This competitive framework generates novel training data constructed from scratch, harnessing the strengths of all participants. Experimental results demonstrate that WarriorCoder achieves competitive performance compared to previous methods, even without relying on proprietary LLMs.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
orGAN: A Synthetic Data Augmentation Pipeline for Simultaneous Generation of Surgical Images and Ground Truth Labels
Graph-Convolutional-Beta-VAE for Synthetic Abdominal Aorta Aneurysm Generation
An Explainable Deep Learning Framework for Brain Stroke and Tumor Progression via MRI Interpretation
A Novel Data Augmentation Approach for Automatic Speaking Assessment on Opinion Expressions
SenseShift6D: Multimodal RGB-D Benchmarking for Robust 6D Pose Estimation across Environment and Sensor Variations
Step-wise Policy for Rare-tool Knowledge (SPaRK): Offline RL that Drives Diverse Tool Use in LLMs
토론
이 논문과 연결된 포럼 글이 아직 없습니다.