# Natural Language Inference on MNLI Unknown Bias (in-distribution) Source: [Natural Language Inference on MNLI Unknown Bias (in-distribution)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:28:05.084Z Evaluation of Natural Language Inference performance on the in-distribution subset of MNLI specifically targeting unknown biases. 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 | Natural Language Inference | | Dataset (including any stated split) | MNLI Unknown Bias (in-distribution) | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 13 of 13 | | 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 | | --- | --- | --- | --- | | CE | 84.2 | Not recorded | 68fa6b341e209131cea2cdc0 | | LMinTemps | 83.3 | Not recorded | 68fa6b341e209131cea2cdc0 | | LMin | 83.1 | Not recorded | 68fa6b341e209131cea2cdc0 | | LMinDirichlet | 82.7 | Not recorded | 68fa6b341e209131cea2cdc0 | | PoEDirichlet | 82.3 | Not recorded | 68fa6b341e209131cea2cdc0 | | PoETemps | 82.1 | Not recorded | 68fa6b341e209131cea2cdc0 | | DRiFtDirichlet | 81.9 | Not recorded | 68fa6b341e209131cea2cdc0 | | DRiFtTemps | 81.5 | Not recorded | 68fa6b341e209131cea2cdc0 | | InvRDirichlet | 81.5 | Not recorded | 68fa6b341e209131cea2cdc0 | | InvRTemps | 81.4 | Not recorded | 68fa6b341e209131cea2cdc0 | | PoE | 80.7 | Not recorded | 68fa6b341e209131cea2cdc0 | | DRiFt | 80.2 | Not recorded | 68fa6b341e209131cea2cdc0 | | InvR | 78.7 | Not recorded | 68fa6b341e209131cea2cdc0 | ### CE Accuracy: 84.2. Result ID: 698e7112ffc3901de09d9ee9. [Reporting paper]() Recorded evaluation configuration: {"Calibrator":"None"}. This record does not assert independent reproduction. ### LMinTemps Accuracy: 83.3. Result ID: 698e7112ffc3901de09d9ef4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Calibrator":"Temperature Scaling"}. This record does not assert independent reproduction. ### LMin Accuracy: 83.1. Result ID: 698e7112ffc3901de09d9ef3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Calibrator":"None"}. This record does not assert independent reproduction. ### LMinDirichlet Accuracy: 82.7. Result ID: 698e7112ffc3901de09d9ef5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Calibrator":"Dirichlet"}. This record does not assert independent reproduction. ### PoEDirichlet Accuracy: 82.3. Result ID: 698e7112ffc3901de09d9eec. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Calibrator":"Dirichlet"}. This record does not assert independent reproduction. ### PoETemps Accuracy: 82.1. Result ID: 698e7112ffc3901de09d9eeb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Calibrator":"Temperature Scaling"}. This record does not assert independent reproduction. ### DRiFtDirichlet Accuracy: 81.9. Result ID: 698e7112ffc3901de09d9eef. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Calibrator":"Dirichlet"}. This record does not assert independent reproduction. ### DRiFtTemps Accuracy: 81.5. Result ID: 698e7112ffc3901de09d9eee. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Calibrator":"Temperature Scaling"}. This record does not assert independent reproduction. ### InvRDirichlet Accuracy: 81.5. Result ID: 698e7112ffc3901de09d9ef2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Calibrator":"Dirichlet"}. This record does not assert independent reproduction. ### InvRTemps Accuracy: 81.4. Result ID: 698e7112ffc3901de09d9ef1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Calibrator":"Temperature Scaling"}. This record does not assert independent reproduction. ### PoE Accuracy: 80.7. Result ID: 698e7112ffc3901de09d9eea. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Calibrator":"None"}. This record does not assert independent reproduction. ### DRiFt Accuracy: 80.2. Result ID: 698e7112ffc3901de09d9eed. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Calibrator":"None"}. This record does not assert independent reproduction. ### InvR Accuracy: 78.7. Result ID: 698e7112ffc3901de09d9ef0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Calibrator":"None"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.