按年被提到
20232023 · 1 次2026
大模型与语言模型›大模型预训练与缩放·arXiv:2304.12244 · cs.CL

WizardLM: Empowering large pre-trained language models to follow complex instructions

Can Xu, Qingfeng Sun, Kai Zheng, Xiubo Geng, Pu Zhao, Jiazhan Feng, Chongyang Tao, Qingwei Lin, Daxin Jiang · 2023
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2023-05-03 · 最近 2024-12-05
2不同的人
2活跃月份
2讨论串
459被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Training large language models (LLMs) with open-domain instruction following data brings colossal success. However, manually creating such instruction data is very time-consuming and labor-intensive. Moreover, humans may struggle to produce high-complexity instructions. In this paper, we show an avenue for creating large amounts of instruction data with varying levels of complexity using LLM instead of humans. Starting with an initial set of instructions, we use our proposed Evol-Instruct to rewrite them step by step into more complex instructions. Then, we mix all generated instruction data to fine-tune LLaMA. We call the resulting model WizardLM. Human evaluations on a complexity-balanced test bed and Vicuna's testset show that instructions from Evol-Instruct are superior to human-created ones. By analyzing the human evaluation results of the high complexity part, we demonstrate that outputs from our WizardLM are preferred to outputs from OpenAI ChatGPT. In GPT-4 automatic evaluation, WizardLM achieves more than 90\% capacity of ChatGPT on 17 out of 29 skills. Even though WizardLM still lags behind ChatGPT in some aspects, our findings suggest that fine-tuning with AI-evolved instructions is a promising direction for enhancing LLMs. Our code and data are public at https://github.com/nlpxucan/WizardLM

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论Mathnerd314 · 2024-12

“Well, look at the process of training a chatbot: - first you make a "raw" corpus, with all the information needed to produce an answer - then you generate sample question-answer pairs - then you use AI to make better questions and better answers (look at e.g. WizardLM https://arxiv.org/pdf/2304.12244) - can also finetune with RLHF or modify the Q-A pa…”

Diátaxis – A systematic approach to technical documentation authoring原评论 ↗
被提交为 story · 1 次