AIstorian 让 AI 成为历史学家：一种用于准确传记生成的知识图谱驱动多智能体系统
AIstorian lets AI be a historian: A KG-powered multi-agent system for accurate biography generation
AI总结：
本文提出 AIstorian 多智能体系统，通过 KG 驱动 RAG、防幻觉纠错及风格微调提升历史传记生成的事实准确性与文风一致性。
摘要：
华为始终致力于探索人工智能在历史研究中的应用。传记生成作为生成式摘要的一种专门形式，在历史研究中发挥着关键作用，但也面临现有大型语言模型（LLM）难以应对的独特挑战。这些挑战包括保持对历史写作惯例的风格遵循、确保事实忠实性，以及处理跨多个文档的碎片化信息。我们提出 AIstorian，这是一种新颖的端到端智能体系统，具备知识图谱（KG）驱动的检索增强生成（RAG）和防幻觉多智能体。具体而言，AIstorian 引入了基于上下文学习的分块策略以及基于 KG 的索引，以准确、高效地检索参考文献。同时，AIstorian 编排多个智能体执行即时幻觉检测和感知错误类型的纠错。此外，为教会 LLM 某种语言风格，我们基于两阶段训练方法对 LLM 进行微调，该方法结合了数据增强增强的监督微调与风格偏好优化。在真实历史进士数据集上的大量实验表明，与现有基线相比，AIstorian 在事实准确性上实现 3.8 倍提升，幻觉率降低 47.6%。数据和代码可在 https://github.com/ZJU-DAILY/AIstorian 获取。
英文摘要：
Huawei has always been committed to exploring the AI application in historical research. Biography generation, as a specialized form of abstractive summarization, plays a crucial role in historical research but faces unique challenges that existing large language models (LLMs) struggle to address. These challenges include maintaining stylistic adherence to historical writing conventions, ensuring factual fidelity, and handling fragmented information across multiple documents. We present AIstorian, a novel end-to-end agentic system featured with a knowledge graph (KG)-powered retrieval-augmented generation (RAG) and anti-hallucination multi-agents. Specifically, AIstorian introduces an in-context learning based chunking strategy and a KG-based index for accurate and efficient reference retrieval. Meanwhile, AIstorian orchestrates multi-agents to conduct on-the-fly hallucination detection and error-type-aware correction. Additionally, to teach LLMs a certain language style, we finetune LLMs based on a two-step training approach combining data augmentation-enhanced supervised fine-tuning with stylistic preference optimization. Extensive experiments on a real-life historical Jinshi dataset demonstrate that AIstorian achieves a 3.8x improvement in factual accuracy and a 47.6% reduction in hallucination rate compared to existing baselines. The data and code are available at: https://github.com/ZJU-DAILY/AIstorian.
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。
