Living Library turns digital archives into in-person conversational exhibits
The Living Library: Transforming Archival Collections into Conversational Knowledge Systems -- Lessons from the Theodore Roosevelt Presidential Library
Computer Vision and Pattern Recognition
Summary
Many digital archives are disorganized and hard to explore. The authors designed the Living Library system to fix this by turning archival records into interactive, face-to-face exhibits where visitors can talk with historical figures. Using the example of Theodore Roosevelt’s library, their system digitizes and organizes records, uses AI to understand and retrieve information, and powers a lifelike digital Roosevelt who answers questions based on historical facts. This approach helps visitors engage directly with history in a believable conversation without making things up.
What this means in practice
- •For museum exhibit designers: Create interactive exhibits where visitors engage in live conversations with historical figures using AI-powered digital humans grounded in archival data.
- •For digital archivists: Use the Living Library framework to digitize, enrich, and publish archival collections for conversational access, improving public engagement with cultural heritage.
Authors
Pengce Wang, Lucia Ronchi Darre, Matt Briney, Michaell Bakalars, Dan Rutkowski, Ursula Hardy, David Wolf, Laura Hoffman, Allen Kim, Shawn Wright, Juan Lavista Ferres
Abstract
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.