# Table-based Fact Verification on TabFact 1.0 (val) Source: [Table-based Fact Verification on TabFact 1.0 (val)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:27:39.344Z Evaluation of model performance on the validation split of the TabFact 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 1.0 (val) | | 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 | | --- | --- | --- | --- | | Table-BERT | 66.1 | Not recorded | 68fa67ba1e209131cea18269 | | Table-BERT | 66 | Not recorded | 68fa67ba1e209131cea18269 | | LPA-Ranking | 65.2 | Not recorded | 68fa67ba1e209131cea18269 | | LPA-Ranking w/ Discriminator (Caption) | 65.1 | Not recorded | 68fa67ba1e209131cea18269 | | NSM w/ LPA-guided ML + RL | 63.2 | Not recorded | 68fa67ba1e209131cea18269 | | LPA-Weighted-Voting | 62.5 | Not recorded | 68fa67ba1e209131cea18269 | | LPA-Voting | 57.7 | Not recorded | 68fa67ba1e209131cea18269 | | Table-BERT | 56.7 | Not recorded | 68fa67ba1e209131cea18269 | | Table-BERT | 56.7 | Not recorded | 68fa67ba1e209131cea18269 | | NSM w/ RL (Binary Reward) | 54.1 | Not recorded | 68fa67ba1e209131cea18269 | | BERT classifier w/o Table | 50.9 | Not recorded | 68fa67ba1e209131cea18269 | | Table-BERT | 50.7 | Not recorded | 68fa67ba1e209131cea18269 | ### Table-BERT Accuracy: 66.1. Result ID: 698d42658b517eb433202d50. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Linearization scan direction":"Horizontal","Sequence order":"Table then Fact","Linearization strategy":"Template"}. This record does not assert independent reproduction. ### Table-BERT Accuracy: 66. Result ID: 698d42658b517eb433202d4f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Linearization scan direction":"Horizontal","Sequence order":"Fact then Table","Linearization strategy":"Template"}. This record does not assert independent reproduction. ### LPA-Ranking Accuracy: 65.2. Result ID: 698d42658b517eb433202d55. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Discriminator usage":"Ranking discriminator","Aggregation":"Top-1 selection"}. This record does not assert independent reproduction. ### LPA-Ranking w/ Discriminator (Caption) Accuracy: 65.1. Result ID: 698d42658b517eb433202d56. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Discriminator usage":"Ranking discriminator","Input":"Caption as sequence"}. This record does not assert independent reproduction. ### NSM w/ LPA-guided ML + RL Accuracy: 63.2. Result ID: 698d42658b517eb433202d52. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Learning strategy":"LPA-guided ML + RL"}. This record does not assert independent reproduction. ### LPA-Weighted-Voting Accuracy: 62.5. Result ID: 698d42658b517eb433202d54. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Discriminator usage":"Confidence weights","Aggregation":"Weighted Voting"}. This record does not assert independent reproduction. ### LPA-Voting Accuracy: 57.7. Result ID: 698d42658b517eb433202d53. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Discriminator usage":"None","Aggregation":"Simple Voting"}. This record does not assert independent reproduction. ### Table-BERT Accuracy: 56.7. Result ID: 698d42658b517eb433202d4d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Linearization scan direction":"Vertical","Sequence order":"Fact then Table","Linearization strategy":"Template"}. This record does not assert independent reproduction. ### Table-BERT Accuracy: 56.7. Result ID: 698d42658b517eb433202d4e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Linearization scan direction":"Vertical","Sequence order":"Table then Fact","Linearization strategy":"Template"}. This record does not assert independent reproduction. ### NSM w/ RL (Binary Reward) Accuracy: 54.1. Result ID: 698d42658b517eb433202d51. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Learning strategy":"Reinforcement Learning","Reward":"Binary"}. This record does not assert independent reproduction. ### BERT classifier w/o Table Accuracy: 50.9. Result ID: 698d42658b517eb433202d4b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Input":"Fact only"}. This record does not assert independent reproduction. ### Table-BERT Accuracy: 50.7. Result ID: 698d42658b517eb433202d4c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Linearization scan direction":"Horizontal","Sequence order":"Fact then Table","Linearization strategy":"Concatenate"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.