FActScore

What it measures

Decomposes long-form biographies/articles into atomic factual claims and verifies each claim against Wikipedia/retrieval sources.

Reading the measurement

Accuracy is only part of the picture. Inspect unsupported answers, abstentions, language coverage and the evidence available to the model. A confident response can still be wrong, and a broad average can hide a specialist gap.

Published evaluation

FActScore · estimator A; Unlabeled entity-biography evaluation. The table retains the source’s reported model and evaluation configuration.

Where this fits in an evaluation suite

Read accuracy together with error and abstention rates. Domain averages can hide language gaps, specialist failures, and poorly calibrated confidence.

Start with a capability hypothesis, then choose a second test with a different failure mode. Keep the checkpoint, reasoning effort, agent tools, sampling policy, and scoring procedure fixed when measuring a training intervention. Record failures and missing outputs in the denominator.

A reproducible comparison

FActScore · estimator A; Unlabeled entity-biography evaluation. The table retains the source’s reported model and evaluation configuration.

Publish the exact run configuration, item coverage, score units, and available uncertainty. If a source supplies only an aggregate or a single run, preserve that limit. A new model name or a rounded score alone does not establish a capability improvement.