Unmediated AI-Assisted Scholarly Citations

TL;DR

This paper introduces an architecture combining language models with direct database access to improve the reliability of AI-assisted scholarly citations, ensuring accurate and verified references through a conversational interface.

Contribution

The authors present the Model Context Protocol, enabling language models to search and verify bibliographic data directly from authoritative sources during scholarly interactions.

Findings

System successfully integrates LLM chatbots with DBLP database.

Ensures citation accuracy by bypassing LLM during final data export.

Demonstrates adaptability to various bibliographic databases.

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 write text with informal citation fragments, which are automatically resolved to proper references. However, language models are not reliable for scholarly work as they generate fabricated (hallucinated) citations at substantial rates. 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: entries are fetched 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 academic data sources.