DeepWriter: A Fact-Grounded Multimodal Writing Assistant Based On Offline Knowledge Base
This addresses the need for reliable, fact-grounded writing assistants in domains like finance, medicine, and law, though it is incremental as it builds on retrieval-augmented methods.
The paper tackles the problem of LLMs lacking domain-specific knowledge and hallucinating in specialized writing tasks by introducing DeepWriter, a multimodal assistant based on an offline knowledge base, which experiments show produces financial reports with higher factual accuracy and quality than existing baselines.
Large Language Models (LLMs) have demonstrated remarkable capabilities in various applications. However, their use as writing assistants in specialized domains like finance, medicine, and law is often hampered by a lack of deep domain-specific knowledge and a tendency to hallucinate. Existing solutions, such as Retrieval-Augmented Generation (RAG), can suffer from inconsistency across multiple retrieval steps, while online search-based methods often degrade quality due to unreliable web content. To address these challenges, we introduce DeepWriter, a customizable, multimodal, long-form writing assistant that operates on a curated, offline knowledge base. DeepWriter leverages a novel pipeline that involves task decomposition, outline generation, multimodal retrieval, and section-by-section composition with reflection. By deeply mining information from a structured corpus and incorporating both textual and visual elements, DeepWriter generates coherent, factually grounded, and professional-grade documents. We also propose a hierarchical knowledge representation to enhance retrieval efficiency and accuracy. Our experiments on financial report generation demonstrate that DeepWriter produces high-quality, verifiable articles that surpasses existing baselines in factual accuracy and generated content quality.