发表机构
Microsoft; TRPL（微软; 西奥多·罗斯福总统图书馆）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出活图书馆框架，通过四层架构将档案转化为对话式展览，并在罗斯福总统图书馆部署，实现300,000条记录的AI处理与数字人互动，提供可迁移的档案对话化经验。
AI 中文摘要
我们提出了活图书馆（Living Library），这是一个端到端框架，用于将分散的数字档案转化为受治理的、对话式的、现场展览体验。该框架在西奥多·罗斯福总统图书馆开发并部署，包含四个层次：数字化与语料库构建、AI驱动的处理、检索与推理，以及一个可选的具身对话界面。前三个层次聚合了一个包含300,000条记录的收藏，应用OCR和结构化元数据增强以供专家策展审查，并将记录发布到混合密集/语义索引中。专家审查通过档案管理员应用（Archivist App）进行，这是一个面向策展人的界面，支持对AI生成的转录和元数据进行修正。受治理的语料库同时支持面向研究者的界面和与TR对话（Talk to TR），后者是一个持续运行的展览，将西奥多·罗斯福以全尺寸数字人的形式呈现在博物馆环境中。为了支持实时的面对面互动，跨时代类比接地（Cross-Era Analogical Grounding）通过有文献记载的历史类比重新构建当代问题，使罗斯福能够在不虚构事实的情况下回应现代话题。双路径检索和端到端流式传输确保回答有依据且响应迅速。分层看门狗、访客会话隔离、自动对话管理以及可独立重启的服务，使得数百名访客的无人值守运行可靠。化身逼真度、空间音频、灯光、舞台设计和对话设计作为整体体验进行开发和评估。我们没有报告受控基准，而是描述了将Talk to TR作为公共展览运营的经验教训，并提供了一个可迁移的模型，用于将档案收藏转化为可信的、现场对话体验。
英文摘要
We present the Living Library, an end-to-end framework for transforming fragmented digital archives into governed, conversational, in-person exhibit experiences. Developed and deployed at the Theodore Roosevelt Presidential Library, the framework comprises four layers: digitization and corpus creation, AI-powered processing, retrieval and reasoning, and an optional embodied conversational interface. The first three layers aggregate a 300,000-record collection, apply OCR and structured metadata enrichment for expert curatorial review, and publish records to a hybrid dense/semantic index. Expert review is conducted through the Archivist App, a curator-facing interface that supports correction of AI-generated transcriptions and metadata. The governed corpus powers both a researcher-facing interface and Talk to TR, a continuously operating exhibit that embodies Theodore Roosevelt as a full-scale digital human within a museum environment. To support live, face-to-face interactions, Cross-Era Analogical Grounding reframes contemporary questions through documented historical parallels, allowing Roosevelt to address present-day topics without inventing facts. Dual-path retrieval and end-to-end streaming keep responses grounded and responsive. Layered watchdogs, visitor-session isolation, automated conversation management, and independently restartable services enable reliable unattended operation for hundreds of visitors. Avatar realism, spatial audio, lighting, staging, and conversational design are developed and evaluated as an integrated experience. Rather than report a controlled benchmark, we describe lessons from operating Talk to TR as a public exhibit and offer a transferable model for transforming archival collections into believable, in-person conversational experiences.
Comments25 pages, 6 figures, 4 tables
