arXiv 2401.172682024-01-30cs.CLcs.AIcs.LG

Weaver：面向创意写作的基础模型

Weaver: Foundation Models for Creative Writing

AIWaves Inc.（AIWaves 公司）

Tiannan Wang, Jiamin Chen, Qingrui Jia, Shuai Wang, Ruoyu Fang, Huilin Wang, Zhaowei Gao, Chunzhao Xie, Chuou Xu, Jihong Dai, Yibin Liu, Jialong Wu, Shengwei Di… 展开作者

Tiannan Wang, Jiamin Chen, Qingrui Jia, Shuai Wang, Ruoyu Fang, Huilin Wang, Zhaowei Gao, Chunzhao Xie, Chuou Xu, Jihong Dai, Yibin Liu, Jialong Wu, Shengwei Ding, Long Li, Zhiwei Huang, Xinle Deng, Teng Yu, Gangan Ma, Han Xiao, Zixin Chen, Danjun Xiang, Yunxia Wang, Yuanyuan Zhu, Yi Xiao, Jing Wang, Yiru Wang, Siran Ding, Jiayang Huang, Jiayi Xu, Yilihamu Tayier, Zhenyu Hu, Yuan Gao, Chengfeng Zheng, Yueshu Ye, Yihang Li, Lei Wan, Xinyue Jiang, Yujie Wang, Siyu Cheng, Zhule Song, Xiangru Tang, Xiaohua Xu, Ningyu Zhang, Huajun Chen, Yuchen Eleanor Jiang, Wangchunshu Zhou

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本研究推出专用于内容创作的大语言模型系列Weaver，通过专用语料预训练、偏好对齐等方法实现多规模模型调度，写作能力超越更大规模通用模型，还支持RAG与工具调用，并总结了领域大模型训练最佳实践。

摘要：

本研究推出Weaver——我们首个专用于内容创作的大语言模型（LLM）系列。Weaver在经过精心筛选的语料库上进行预训练，重点提升大语言模型的写作能力。随后，我们针对创意写作与专业写作场景对Weaver进行微调，并采用一套全新的指令数据合成与大语言模型对齐方法，使其与专业写作者的偏好对齐，从而能够生成更具人类风格的文本，且能遵循更多样化的内容创作指令。\nWeaver系列包含Weaver Mini（1.8B）、Weaver Base（6B）、Weaver Pro（14B）和Weaver Ultra（34B）四种规模的模型，适配不同应用场景，还可由路由智能体根据查询复杂度动态调度，以平衡响应质量与计算成本。在精心构建的大语言模型写作能力评估基准上的测试显示，所有规模的Weaver模型表现均优于数倍于其规模的通用大语言模型。值得注意的是，我们性能最强的Weaver Ultra模型在多种写作场景下超越了当前最先进的通用大语言模型GPT-4，证明了针对写作任务训练专用大语言模型的优势。\n此外，Weaver原生支持检索增强生成（RAG）和函数调用（工具使用）。我们展示了这些能力在改进AI辅助写作系统方面的多种用例，包括整合外部知识库、工具或API，以及提供个性化写作辅助。我们还讨论并总结了领域专用大语言模型预训练与微调的指导原则与最佳实践。

英文摘要：

This work introduces Weaver, our first family of large language models (LLMs) dedicated to content creation. Weaver is pre-trained on a carefully selected corpus that focuses on improving the writing capabilities of large language models. We then fine-tune Weaver for creative and professional writing purposes and align it to the preference of professional writers using a suit of novel methods for instruction data synthesis and LLM alignment, making it able to produce more human-like texts and follow more diverse instructions for content creation. The Weaver family consists of models of Weaver Mini (1.8B), Weaver Base (6B), Weaver Pro (14B), and Weaver Ultra (34B) sizes, suitable for different applications and can be dynamically dispatched by a routing agent according to query complexity to balance response quality and computation cost. Evaluation on a carefully curated benchmark for assessing the writing capabilities of LLMs shows Weaver models of all sizes outperform generalist LLMs several times larger than them. Notably, our most-capable Weaver Ultra model surpasses GPT-4, a state-of-the-art generalist LLM, on various writing scenarios, demonstrating the advantage of training specialized LLMs for writing purposes. Moreover, Weaver natively supports retrieval-augmented generation (RAG) and function calling (tool usage). We present various use cases of these abilities for improving AI-assisted writing systems, including integration of external knowledge bases, tools, or APIs, and providing personalized writing assistance. Furthermore, we discuss and summarize a guideline and best practices for pre-training and fine-tuning domain-specific LLMs.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。