Unmediated AI-Assisted Scholarly Citations

Abstract

Traditional bibliography databases require users to navigate search forms and manually copy citation data. Language models offer an alternative: a natural-language interface where researchers can write text with informal citation fragments and have them automatically resolved to proper references. However, language models generate fabricated (hallucinated) citations at substantial rates, making them unreliable for scholarly work. We present an architectural approach that combines the natural language interface of LLM chatbots with the accuracy of direct database access, implemented through the Model Context Protocol. Our system enables language models to search bibliographic databases, perform fuzzy matching, and export verified entries, all through conversational interaction. A key architectural principle bypasses the language model during final data export by fetching entries directly from authoritative sources, with timeout protection, to guarantee accuracy. We demonstrate this approach with MCP-DBLP, a server providing access to the DBLP computer science bibliography. The system transforms form-based bibliographic services into conversational assistants that maintain scholarly integrity. This architecture is adaptable to other bibliographic databases and scholarly data sources.