# Table-based Fact Verification on TabFact simple 1.0 (test) Source: [Table-based Fact Verification on TabFact simple 1.0 (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:33:03.207Z Evaluation of model performance on the test split of the TabFact simple 1.0 dataset for Table-based Fact Verification, reporting Accuracy. 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 | Table-based Fact Verification | | Dataset (including any stated split) | TabFact simple 1.0 (test) | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 12 of 12 | | 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. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Salience-aware learning system | 93.6 | Not recorded | 68fa6ab91e209131cea2a0f3 | | Salience-aware learning system | 93.4 | Not recorded | 68fa6ab91e209131cea2a0f3 | | Salience-aware learning system | 93.3 | Not recorded | 68fa6ab91e209131cea2a0f3 | | TAPAS | 92.3 | Not recorded | 68fa6ab91e209131cea2a0f3 | | TAPAS | 89 | Not recorded | 68fa6ab91e209131cea2a0f3 | | ProgVGAT | 88.3 | Not recorded | 68fa6ab91e209131cea2a0f3 | | HeterTFV | 85.9 | Not recorded | 68fa6ab91e209131cea2a0f3 | | LogicalFactChecker | 85.4 | Not recorded | 68fa6ab91e209131cea2a0f3 | | Table-BERT | 79.1 | Not recorded | 68fa6ab91e209131cea2a0f3 | | Table-BERT-Horizontal-F+T-Template | 79 | Not recorded | 68fa67ba1e209131cea18269 | | LPA-Ranking w/ Discriminator (Caption) | 78.7 | Not recorded | 68fa67ba1e209131cea18269 | | LPA | 78.4 | Not recorded | 68fa6ab91e209131cea2a0f3 | ### Salience-aware learning system Accuracy: 93.6. Result ID: 699acff15698665ec45ed676. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Method Type":"Non-logical program-driven","Configuration":"w/o auxiliary task"}. This record does not assert independent reproduction. ### Salience-aware learning system Accuracy: 93.4. Result ID: 699acff15698665ec45ed675. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Method Type":"Non-logical program-driven","Configuration":"w/o augmented data"}. This record does not assert independent reproduction. ### Salience-aware learning system Accuracy: 93.3. Result ID: 699acff15698665ec45ed674. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Method Type":"Non-logical program-driven","Configuration":"Full system"}. This record does not assert independent reproduction. ### TAPAS Accuracy: 92.3. Result ID: 699acff15698665ec45ed673. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Method Type":"Non-logical program-driven","Reference":"Eisenschlos et al., 2020"}. This record does not assert independent reproduction. ### TAPAS Accuracy: 89. Result ID: 699acff15698665ec45ed672. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Method Type":"Non-logical program-driven","Reference":"Dong and Smith, 2021"}. This record does not assert independent reproduction. ### ProgVGAT Accuracy: 88.3. Result ID: 699acff15698665ec45ed670. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Method Type":"Logical program-driven"}. This record does not assert independent reproduction. ### HeterTFV Accuracy: 85.9. Result ID: 699acff15698665ec45ed66f. [Reporting paper]() Recorded evaluation configuration: {"Method Type":"Logical program-driven"}. This record does not assert independent reproduction. ### LogicalFactChecker Accuracy: 85.4. Result ID: 699acff15698665ec45ed66e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Method Type":"Logical program-driven"}. This record does not assert independent reproduction. ### Table-BERT Accuracy: 79.1. Result ID: 699acff15698665ec45ed671. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Method Type":"Non-logical program-driven"}. This record does not assert independent reproduction. ### Table-BERT-Horizontal-F+T-Template Accuracy: 79. Result ID: 698d42658b517eb433202d63. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Linearization scan direction":"Horizontal","Linearization strategy":"Template"}. This record does not assert independent reproduction. ### LPA-Ranking w/ Discriminator (Caption) Accuracy: 78.7. Result ID: 698d42658b517eb433202d64. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Discriminator usage":"Ranking discriminator"}. This record does not assert independent reproduction. ### LPA Accuracy: 78.4. Result ID: 699acff15698665ec45ed66d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Method Type":"Logical program-driven"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.