CoAuthorAI: A Human in the Loop System For Scientific Book Writing
This addresses the challenge of producing consistent and reliable scientific books for researchers and publishers, representing an incremental improvement by extending LLM capabilities from articles to books through systematic collaboration.
The authors tackled the problem of LLMs struggling with book-length scientific writing by introducing CoAuthorAI, a human-in-the-loop system that achieved a maximum soft-heading recall of 98% in evaluations and an 82% satisfaction rate in human assessments, enabling the publication of a book with Springer Nature.
Large language models (LLMs) are increasingly used in scientific writing but struggle with book-length tasks, often producing inconsistent structure and unreliable citations. We introduce CoAuthorAI, a human-in-the-loop writing system that combines retrieval-augmented generation, expert-designed hierarchical outlines, and automatic reference linking. The system allows experts to iteratively refine text at the sentence level, ensuring coherence and accuracy. In evaluations of 500 multi-domain literature review chapters, CoAuthorAI achieved a maximum soft-heading recall of 98%; in a human evaluation of 100 articles, the generated content reached a satisfaction rate of 82%. The book AI for Rock Dynamics generated with CoAuthorAI and Kexin Technology's LUFFA AI model has been published with Springer Nature. These results show that systematic human-AI collaboration can extend LLMs' capabilities from articles to full-length books, enabling faster and more reliable scientific publishing.