# Factual mistake detection on DocENT (PoSh) Source: [Factual mistake detection on DocENT (PoSh)]() Collection index: [llms.txt]() Data updated: 2026-05-08T09:57:55.012Z Evaluation of Factual Mistake Detection performance on the DocENT (PoSh) dataset, measured using Accuracy and rank correlation coefficients (Spearman rho and Kendall tau). A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Factual mistake detection | | Dataset (including any stated split) | DocENT (PoSh) | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 6 of 6 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Accuracy](): Higher is better; unit: PERCENT. - [Spearman Rho (ρ)](): Higher is better; unit: SCALAR. - [Kendall Tau (τ)](): Higher is better; unit: SCALAR. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Soft-MSD | 64.8 | Not recorded | 69fd6e145497b3b670c89401 | | Soft-MSD | 64.4 | Not recorded | 69fd6e145497b3b670c89401 | | CLIPScore | 53.5 | Not recorded | 69fd6e145497b3b670c89401 | | CLIPScore | 45.3 | Not recorded | 69fd6e145497b3b670c89401 | | FLEUR | 41.2 | Not recorded | 69fd6e145497b3b670c89401 | | FLEUR | 35.2 | Not recorded | 69fd6e145497b3b670c89401 | ### Soft-MSD Accuracy: 64.8. Result ID: 69fdb39747f34ce924e1212e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Soft-MSD Accuracy: 64.4. Result ID: 69fdb39747f34ce924e12128. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### CLIPScore Accuracy: 53.5. Result ID: 69fdb39747f34ce924e1212c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### CLIPScore Accuracy: 45.3. Result ID: 69fdb39747f34ce924e12126. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### FLEUR Accuracy: 41.2. Result ID: 69fdb39747f34ce924e1212d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### FLEUR Accuracy: 35.2. Result ID: 69fdb39747f34ce924e12127. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.