English(EN)Astraios: Parameter-Efficient Instruction Tuning Code Large Language Models
新的基准和微调方法提升了大型语言模型代码生成能力 · 跟踪3个来源
作者PulseAugur 编辑部·[3 个来源]·
研究人员推出了Astraios,这是一套包含28个指令微调的OctoCoder模型,旨在评估大型语言模型(LLM)的参数高效微调(PEFT)方法。研究发现,全参数微调通常能带来最佳性能,而LoRA则提供了有利的成本效益权衡。此外,还开发了一个名为BigCodeBench的新基准,用于评估LLM使用多样化函数调用和复杂指令进行代码生成的能力,结果显示当前模型在这些任务上的表现与人类相比仍有差距。另一个平台BigCodeArena的创建,通过集成执行环境,为代码生成评估提供了更可靠的人类偏好数据,并指出GPT-5和Claude Opus 4等专有模型在代码生成能力方面处于领先地位。
AI
arXiv:2401.00788v2 Announce Type: replace-cross Abstract: The high cost of full-parameter fine-tuning (FFT) of Large Language Models (LLMs) has led to a series of parameter-efficient fine-tuning (PEFT) methods. However, it remains unclear which methods provide the best cost-perfo…
arXiv cs.AI
TIER_1English(EN)·Terry Yue Zhuo, Minh Chien Vu, Jenny Chim, Han Hu, Wenhao Yu, Ratnadira Widyasari, Imam Nur Bani Yusuf, Haolan Zhan, Junda He, Indraneil Paul, Simon Brunner, Chen Gong, Thong Hoang, Armel Randy Zebaze, Xiaoheng Hong, Wen-Ding Li, Jean Kaddour, Ming Xu, Z…·
arXiv:2406.15877v5 Announce Type: replace-cross Abstract: Task automation has been greatly empowered by the recent advances in Large Language Models (LLMs) via Python code, where the tasks ranging from software engineering development to general-purpose reasoning. While current b…
arXiv:2510.08697v3 Announce Type: replace-cross Abstract: Crowdsourced model evaluation platforms, such as Chatbot Arena, enable real-time evaluation from human perspectives to assess the quality of model responses. In the coding domain, manually examining the quality of LLM-gene…