An Evidence-Grounded Multimodal AI Framework for Historical Digital Personae in Cultural Heritage

Historical digital personas are a promising means of interactive and personalized access to cultural heritage; however, their practical deployment requires simultaneous control over factual accuracy, source provenance, persona consistency, and multimodal response latency. This paper proposes an evidence-grounded multimodal artificial intelligence (AI) framework for historical digital personas that combines controlled canonical interactions with open-ended retrieval-augmented generation. The architecture implements a cascaded query-processing strategy: high-confidence queries are routed to source-linked canonical frequently asked question (FAQ) responses and pre-generated multimedia objects, while open-ended queries are handled via hybrid full-text retrieval, cross-encoder reranking, an Evidence Gate, evidence-constrained generation, persona-oriented post-generation validation, speech synthesis, and lip synchronization. The framework is implemented and evaluated experimentally using the digital persona of Taras Shevchenko based on a Ukrainian-language cultural heritage knowledge base containing 543 evidence-oriented retrieval chunks, 50 canonical FAQ intents, and 500 natural language question variants. BGE-M3 hybrid retrieval achieved a Recall@1 of 36.46% and a Recall@10 of 77.71%, outperforming classical BM25 and compact dense retrieval baselines. Chunk-level cross-encoder reranking increased Recall@10 to 87.92% and normalized discounted cumulative gain at 10 (nDCG@10) to 0.6151. In a strict Leave-One-Variant-Out evaluation, the conservative FAQ cascade reached a coverage of 87.4% and a correctness of 95.19% among accepted matches. The Evidence Gate correctly rejected 96% of unsupported queries while retaining 88% of evidence-supported queries, achieving a Balanced Accuracy of 92%. Canonical multimedia caching reduced median processing time from approximately 143.94 s for complete dynamic multimedia executions to approximately 2.08 ms for processing-layer access to prepared canonical media under the evaluated warm-cache configuration. The results show that robust construction of historical digital personas requires a functional separation between high-confidence canonical interactions and open-ended, evidence-grounded generation, as well as coordinated yet functionally decoupled operation of retrieval, provenance, persona control, and multimedia delivery.