# Fact Extraction and Verification on FEVER (test) Source: [Fact Extraction and Verification on FEVER (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:48:24.046Z Evaluation of model performance on the test split of the FEVER dataset for Fact Extraction and Verification, reporting F1, LA, and FS scores. 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 | Fact Extraction and Verification | | Dataset (including any stated split) | FEVER (test) | | Metric | Label Accuracy (LA) | | 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 - [Label Accuracy (LA)](): Higher is better; unit: PERCENT. - [F1 Score](): Higher is better; unit: PERCENT. - [Fact Score (FS)](): Higher is better; unit: PERCENT. - [FEVER Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | Label Accuracy (LA) | Result date | Report paper | | --- | --- | --- | --- | | KGAT (CorefRoBERTa\_LARGE) | 75.96 | Not recorded | 68fa686b1e209131cea1bff4 | | KGAT (CorefBERT\_LARGE) | 74.37 | Not recorded | 68fa686b1e209131cea1bff4 | | KGAT | 74.07 | Not recorded | 68fa686b1e209131cea1bff4 | | KGAT | 73.61 | Not recorded | 68fa686b1e209131cea1bff4 | | CICD | 73.1 | Not recorded | 68fa6a051e209131cea257af | | KGAT (CorefBERT\_BASE) | 72.88 | Not recorded | 68fa686b1e209131cea1bff4 | | KGAT | 72.81 | Not recorded | 68fa686b1e209131cea1bff4 | | Full system (single) | 72.56 | Not recorded | 68fa66641e209131cea100b8 | | SR-MRS | 72.56 | Not recorded | 68fa686b1e209131cea1bff4 | | GEAR | 71.6 | Not recorded | 68fa686b1e209131cea1bff4 | | KGAT | 71.6 | Not recorded | 68fa6a051e209131cea257af | | BERT Concat | 71.01 | Not recorded | 68fa686b1e209131cea1bff4 | | GEAR | 70.8 | Not recorded | 68fa6a051e209131cea257af | | Nie (2019) | 68.16 | Not recorded | 68fa66641e209131cea100b8 | | Yoneda (2018) | 67.44 | Not recorded | 68fa66641e209131cea100b8 | | HAN | 66.9 | Not recorded | 68fa6a051e209131cea257af | | Hanselowski (2018) | 65.22 | Not recorded | 68fa66641e209131cea100b8 | | NSMN | 62.1 | Not recorded | 68fa6a051e209131cea257af | ### KGAT (CorefRoBERTa\_LARGE) Label Accuracy (LA): 75.96. Result ID: 698d6e318b517eb433217112. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"CorefRoBERTa\_LARGE"}. This record does not assert independent reproduction. ### KGAT (CorefBERT\_LARGE) Label Accuracy (LA): 74.37. Result ID: 698d6e318b517eb433217110. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"CorefBERT\_LARGE"}. This record does not assert independent reproduction. ### KGAT Label Accuracy (LA): 74.07. Result ID: 698d6e318b517eb433217111. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"RoBERTa\_LARGE"}. This record does not assert independent reproduction. ### KGAT Label Accuracy (LA): 73.61. Result ID: 698d6e318b517eb43321710f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"BERT\_LARGE"}. This record does not assert independent reproduction. ### CICD Label Accuracy (LA): 73.1. Result ID: 698dfec4ffc3901de09a0509. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### KGAT (CorefBERT\_BASE) Label Accuracy (LA): 72.88. Result ID: 698d6e318b517eb43321710e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"CorefBERT\_BASE"}. This record does not assert independent reproduction. ### KGAT Label Accuracy (LA): 72.81. Result ID: 698d6e318b517eb43321710d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"BERT\_BASE"}. This record does not assert independent reproduction. ### Full system (single) Label Accuracy (LA): 72.56. Result ID: 698cef3b8b517eb4331dce98. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Mode":"single"}. This record does not assert independent reproduction. ### SR-MRS Label Accuracy (LA): 72.56. Result ID: 698d6e318b517eb43321710c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"BERT"}. This record does not assert independent reproduction. ### GEAR Label Accuracy (LA): 71.6. Result ID: 698d6e318b517eb43321710b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"BERT"}. This record does not assert independent reproduction. ### KGAT Label Accuracy (LA): 71.6. Result ID: 698dfec4ffc3901de09a0508. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### BERT Concat Label Accuracy (LA): 71.01. Result ID: 698d6e318b517eb43321710a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"BERT"}. This record does not assert independent reproduction. ### GEAR Label Accuracy (LA): 70.8. Result ID: 698dfec4ffc3901de09a0507. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Nie (2019) Label Accuracy (LA): 68.16. Result ID: 698cef3b8b517eb4331dce97. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Yoneda (2018) Label Accuracy (LA): 67.44. Result ID: 698cef3b8b517eb4331dce96. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### HAN Label Accuracy (LA): 66.9. Result ID: 698dfec4ffc3901de09a0506. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Hanselowski (2018) Label Accuracy (LA): 65.22. Result ID: 698cef3b8b517eb4331dce95. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### NSMN Label Accuracy (LA): 62.1. Result ID: 698dfec4ffc3901de09a0505. [Reporting paper]() [Method origin paper]() 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.