_version_ 1866914659758505984
author Wang, Tiannan
Chen, Jiamin
Jia, Qingrui
Wang, Shuai
Fang, Ruoyu
Wang, Huilin
Gao, Zhaowei
Xie, Chunzhao
Xu, Chuou
Dai, Jihong
Liu, Yibin
Wu, Jialong
Ding, Shengwei
Li, Long
Huang, Zhiwei
Deng, Xinle
Yu, Teng
Ma, Gangan
Xiao, Han
Chen, Zixin
Xiang, Danjun
Wang, Yunxia
Zhu, Yuanyuan
Xiao, Yi
Wang, Jing
Wang, Yiru
Ding, Siran
Huang, Jiayang
Xu, Jiayi
Tayier, Yilihamu
Hu, Zhenyu
Gao, Yuan
Zheng, Chengfeng
Ye, Yueshu
Li, Yihang
Wan, Lei
Jiang, Xinyue
Wang, Yujie
Cheng, Siyu
Song, Zhule
Tang, Xiangru
Xu, Xiaohua
Zhang, Ningyu
Chen, Huajun
Jiang, Yuchen Eleanor
Zhou, Wangchunshu
author_facet Wang, Tiannan
Chen, Jiamin
Jia, Qingrui
Wang, Shuai
Fang, Ruoyu
Wang, Huilin
Gao, Zhaowei
Xie, Chunzhao
Xu, Chuou
Dai, Jihong
Liu, Yibin
Wu, Jialong
Ding, Shengwei
Li, Long
Huang, Zhiwei
Deng, Xinle
Yu, Teng
Ma, Gangan
Xiao, Han
Chen, Zixin
Xiang, Danjun
Wang, Yunxia
Zhu, Yuanyuan
Xiao, Yi
Wang, Jing
Wang, Yiru
Ding, Siran
Huang, Jiayang
Xu, Jiayi
Tayier, Yilihamu
Hu, Zhenyu
Gao, Yuan
Zheng, Chengfeng
Ye, Yueshu
Li, Yihang
Wan, Lei
Jiang, Xinyue
Wang, Yujie
Cheng, Siyu
Song, Zhule
Tang, Xiangru
Xu, Xiaohua
Zhang, Ningyu
Chen, Huajun
Jiang, Yuchen Eleanor
Zhou, Wangchunshu
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2401_17268
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Weaver: Foundation Models for Creative Writing
Wang, Tiannan
Chen, Jiamin
Jia, Qingrui
Wang, Shuai
Fang, Ruoyu
Wang, Huilin
Gao, Zhaowei
Xie, Chunzhao
Xu, Chuou
Dai, Jihong
Liu, Yibin
Wu, Jialong
Ding, Shengwei
Li, Long
Huang, Zhiwei
Deng, Xinle
Yu, Teng
Ma, Gangan
Xiao, Han
Chen, Zixin
Xiang, Danjun
Wang, Yunxia
Zhu, Yuanyuan
Xiao, Yi
Wang, Jing
Wang, Yiru
Ding, Siran
Huang, Jiayang
Xu, Jiayi
Tayier, Yilihamu
Hu, Zhenyu
Gao, Yuan
Zheng, Chengfeng
Ye, Yueshu
Li, Yihang
Wan, Lei
Jiang, Xinyue
Wang, Yujie
Cheng, Siyu
Song, Zhule
Tang, Xiangru
Xu, Xiaohua
Zhang, Ningyu
Chen, Huajun
Jiang, Yuchen Eleanor
Zhou, Wangchunshu
Computation and Language
Artificial Intelligence
Machine Learning
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.
title Weaver: Foundation Models for Creative Writing
topic Computation and Language
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2401.17268