Long-form biographies from strong models contain a substantial share of unsupported atomic facts, rising for less well-known subjects.

Capability: Stating false facts confidently

Sources

supportsFActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation
Long-form biographies from strong models contain a substantial share of unsupported atomic facts, rising for less well-known subjects.

Reviewed by AI and Russ MillerLast checked: 2026-09-03Evidence activity

Either way, bring evidence: a link, or what you saw.

Disagreeing is the most useful thing you can do here. Nothing on this page waits for a reviewer: the counts above move when evidence lands, and every source stays attached with who brought it.

Related claims

Models endorse widely held falsehoods, showing weak verification against what they know.Checking claims against evidence
Decomposing long answers into atomic facts and checking each with search catches most errors and beats human annotators on cost and agreement.Stating false facts confidently
Accuracy on a fact scales with how many pretraining documents mention it, so long-tail facts are systematically unreliable.Stating false facts confidently
On verifiable instructions such as length and format constraints, strong models still fail a meaningful share, and failures grow when several constraints apply at once.Following an unfamiliar procedure