# Claim Verification on DIALFACT (test) Source: [Claim Verification on DIALFACT (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:28:12.116Z Evaluation of model performance on the test split of the DIALFACT dataset for Claim Verification, reporting Accuracy and Macro F1. 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 | Claim Verification | | Dataset (including any stated split) | DIALFACT (test) | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 18 of 18 | | 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. - [Macro F1](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Aug-WoW | 69.2 | Not recorded | 68fa6c0f1e209131cea31ce6 | | Colloquial | 63.5 | Not recorded | 68fa6c0f1e209131cea31ce6 | | CorefBert-Colloquial | 61.4 | Not recorded | 68fa6c0f1e209131cea31ce6 | | VitaminC | 57.6 | Not recorded | 68fa6c0f1e209131cea31ce6 | | Aug-WoW | 51.6 | Not recorded | 68fa6c0f1e209131cea31ce6 | | Aug-WoW | 51.5 | Not recorded | 68fa6c0f1e209131cea31ce6 | | Colloquial | 48.7 | Not recorded | 68fa6c0f1e209131cea31ce6 | | Colloquial | 48.1 | Not recorded | 68fa6c0f1e209131cea31ce6 | | CorefBert-Colloquial | 47.6 | Not recorded | 68fa6c0f1e209131cea31ce6 | | CorefBert-Colloquial | 46.4 | Not recorded | 68fa6c0f1e209131cea31ce6 | | VitaminC | 46.2 | Not recorded | 68fa6c0f1e209131cea31ce6 | | VitaminC | 45.9 | Not recorded | 68fa6c0f1e209131cea31ce6 | | DNLI | 43.3 | Not recorded | 68fa6c0f1e209131cea31ce6 | | DNLI | 39.1 | Not recorded | 68fa6c0f1e209131cea31ce6 | | DNLI | 38.4 | Not recorded | 68fa6c0f1e209131cea31ce6 | | DECODE | 37.8 | Not recorded | 68fa6c0f1e209131cea31ce6 | | DECODE | 35.3 | Not recorded | 68fa6c0f1e209131cea31ce6 | | DECODE | 34.5 | Not recorded | 68fa6c0f1e209131cea31ce6 | ### Aug-WoW Accuracy: 69.2. Result ID: 698ec1ecffc3901de0a0d1da. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evidence Setting":"Oracle-Evidence"}. This record does not assert independent reproduction. ### Colloquial Accuracy: 63.5. Result ID: 698ec1ecffc3901de0a0d1d9. [Reporting paper]() Recorded evaluation configuration: {"Evidence Setting":"Oracle-Evidence"}. This record does not assert independent reproduction. ### CorefBert-Colloquial Accuracy: 61.4. Result ID: 698ec1ecffc3901de0a0d1d8. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evidence Setting":"Oracle-Evidence"}. This record does not assert independent reproduction. ### VitaminC Accuracy: 57.6. Result ID: 698ec1ecffc3901de0a0d1d7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evidence Setting":"Oracle-Evidence"}. This record does not assert independent reproduction. ### Aug-WoW Accuracy: 51.6. Result ID: 698ec1ecffc3901de0a0d1e0. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evidence Setting":"Wiki-Evidence"}. This record does not assert independent reproduction. ### Aug-WoW Accuracy: 51.5. Result ID: 698ec1ecffc3901de0a0d1e6. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evidence Setting":"DPR-Evidence"}. This record does not assert independent reproduction. ### Colloquial Accuracy: 48.7. Result ID: 698ec1ecffc3901de0a0d1e5. [Reporting paper]() Recorded evaluation configuration: {"Evidence Setting":"DPR-Evidence"}. This record does not assert independent reproduction. ### Colloquial Accuracy: 48.1. Result ID: 698ec1ecffc3901de0a0d1df. [Reporting paper]() Recorded evaluation configuration: {"Evidence Setting":"Wiki-Evidence"}. This record does not assert independent reproduction. ### CorefBert-Colloquial Accuracy: 47.6. Result ID: 698ec1ecffc3901de0a0d1de. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evidence Setting":"Wiki-Evidence"}. This record does not assert independent reproduction. ### CorefBert-Colloquial Accuracy: 46.4. Result ID: 698ec1ecffc3901de0a0d1e4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evidence Setting":"DPR-Evidence"}. This record does not assert independent reproduction. ### VitaminC Accuracy: 46.2. Result ID: 698ec1ecffc3901de0a0d1dd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evidence Setting":"Wiki-Evidence"}. This record does not assert independent reproduction. ### VitaminC Accuracy: 45.9. Result ID: 698ec1ecffc3901de0a0d1e3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evidence Setting":"DPR-Evidence"}. This record does not assert independent reproduction. ### DNLI Accuracy: 43.3. Result ID: 698ec1ecffc3901de0a0d1d5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evidence Setting":"Oracle-Evidence"}. This record does not assert independent reproduction. ### DNLI Accuracy: 39.1. Result ID: 698ec1ecffc3901de0a0d1db. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evidence Setting":"Wiki-Evidence"}. This record does not assert independent reproduction. ### DNLI Accuracy: 38.4. Result ID: 698ec1ecffc3901de0a0d1e1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evidence Setting":"DPR-Evidence"}. This record does not assert independent reproduction. ### DECODE Accuracy: 37.8. Result ID: 698ec1ecffc3901de0a0d1d6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evidence Setting":"Oracle-Evidence"}. This record does not assert independent reproduction. ### DECODE Accuracy: 35.3. Result ID: 698ec1ecffc3901de0a0d1dc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evidence Setting":"Wiki-Evidence"}. This record does not assert independent reproduction. ### DECODE Accuracy: 34.5. Result ID: 698ec1ecffc3901de0a0d1e2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evidence Setting":"DPR-Evidence"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.