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.

Weaver 是一种专注于内容创作的大型语言模型（LLM）系列，通过精心挑选的语料库进行预训练，再通过创造性和专业写作目的进行微调，使其能够生成更接近人类风格的文本并满足更多样化的内容创作指令。Weaver 系列各个模型规模适用于不同应用，并且可以根据查询复杂性进行动态分配以平衡响应质量和计算成本。评估表明，相较于比它们规模大数倍的综合型 LLM，包括最强的 Weaver Ultra 模型也优于 GPT-4，展示了为写作目的进行专门训练的 LLM 的优势。此外，Weaver 还原生支持检索增强生成（RAG）和函数调用（工具使用），为改进 AI 辅助写作系统提供各种用例和最佳实践指南。

纬纱：创意写作的基础模型

Weaver: Foundation Models for Creative Writing

Current model testing work has mostly focused on creating test cases.
Identifying what to test is a step that is largely ignored and poorly
supported. We propose Weaver, an interactive tool that supports requirements
elicitation for guiding model testing. Weaver uses large language models to
generate knowledge bases and recommends concepts from them interactively,
allowing testers to elicit requirements for further testing. Weaver provides
rich external knowledge to testers and encourages testers to systematically
explore diverse concepts beyond their own biases. In a user study, we show that
both NLP experts and non-experts identified more, as well as more diverse
concepts worth testing when using Weaver. Collectively, they found more than
200 failing test cases for stance detection with zero-shot ChatGPT. Our case
studies further show that Weaver can help practitioners test models in
real-world settings, where developers define more nuanced application scenarios
(e.g., code understanding and transcript summarization) using LLMs.

通过使用大型语言模型和知识库，建议解决方案入手，Weaver 工具支持需求提取，帮助测试人员发现更多、更多样化的概念，用于进一步测试，促使测试人员系统性地探索自己之外的概念，通过用户研究和案例分析表明 Weaver 能帮助测试人员在实际环境中测试模型，并帮助开发者定义更细粒度的应用场景。

超越测试者的偏见：使用知识库指导模型测试

Beyond Testers' Biases: Guiding Model Testing with Knowledge Bases using  LLMs

Recent developments in transfer learning have boosted the advancements in
natural language processing tasks. The performance is, however, dependent on
high-quality, manually annotated training data. Especially in the biomedical
domain, it has been shown that one training corpus is not enough to learn
generic models that are able to efficiently predict on new data. Therefore,
state-of-the-art models need the ability of lifelong learning in order to
improve performance as soon as new data are available - without the need of
retraining the whole model from scratch. We present WEAVER, a simple, yet
efficient post-processing method that infuses old knowledge into the new model,
thereby reducing catastrophic forgetting. We show that applying WEAVER in a
sequential manner results in similar word embedding distributions as doing a
combined training on all data at once, while being computationally more
efficient. Because there is no need of data sharing, the presented method is
also easily applicable to federated learning settings and can for example be
beneficial for the mining of electronic health records from different clinics.

提出了一种称为 WEAVER 的简单且高效的后处理方法，该方法将旧知识融入新模型中，从而减少灾难性遗忘，并且在序列方式下，应用 WEAVER 导致与一次性对所有数据进行联合训练相似的单词嵌入分布，同时具有更高的计算效率。