# Natural Language Inference on XNLI Ur (test) Source: [Natural Language Inference on XNLI Ur (test)]() Collection index: [llms.txt]() Data updated: 2026-04-28T08:44:47.571Z Evaluation of cross-lingual Natural Language Inference performance specifically on the Urdu subset of the XNLI test set, 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 | Natural Language Inference | | Dataset (including any stated split) | XNLI Ur (test) | | Metric | Accuracy | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 26 of 26 | | 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: SCALAR. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Baseline-PS | 0.9643 | Not recorded | 69f03f4a55a3c32af89fa2be | | Tpl-rand-k | 0.6518 | Not recorded | 68fa74281e209131cea6014e | | Tpl-div-k | 0.6501 | Not recorded | 68fa74281e209131cea6014e | | T-div-k | 0.6487 | Not recorded | 68fa74281e209131cea6014e | | SRC+GEN | 0.6464 | Not recorded | 68fa74281e209131cea6014e | | Tpl-top-k | 0.6406 | Not recorded | 68fa74281e209131cea6014e | | SRC+GEN | 0.6381 | Not recorded | 68fa74281e209131cea6014e | | T-top-k | 0.6345 | Not recorded | 68fa74281e209131cea6014e | | Tpl-rand-k | 0.6329 | Not recorded | 68fa74281e209131cea6014e | | Tpl-div-k | 0.6227 | Not recorded | 68fa74281e209131cea6014e | | T-top-k | 0.6202 | Not recorded | 68fa74281e209131cea6014e | | T-rand-k | 0.6186 | Not recorded | 68fa74281e209131cea6014e | | Tpl-top-k | 0.6173 | Not recorded | 68fa74281e209131cea6014e | | SRC | 0.6134 | Not recorded | 68fa74281e209131cea6014e | | Skyline | 0.612 | Not recorded | 69f03f4a55a3c32af89fa2be | | T-div-k | 0.6103 | Not recorded | 68fa74281e209131cea6014e | | T-rand-k | 0.5821 | Not recorded | 68fa74281e209131cea6014e | | GEN | 0.5735 | Not recorded | 68fa74281e209131cea6014e | | GEN | 0.5659 | Not recorded | 68fa74281e209131cea6014e | | SRC | 0.5543 | Not recorded | 68fa74281e209131cea6014e | | XITE-reg-reg | 0.4992 | Not recorded | 69f03f4a55a3c32af89fa2be | | XITE-reg-lda | 0.47 | Not recorded | 69f03f4a55a3c32af89fa2be | | XITE-reg-lda | 0.3695 | Not recorded | 69f03f4a55a3c32af89fa2be | | XITE-reg-reg | 0.344 | Not recorded | 69f03f4a55a3c32af89fa2be | | Skyline | 0.3347 | Not recorded | 69f03f4a55a3c32af89fa2be | | Baseline-PS | 0.316 | Not recorded | 69f03f4a55a3c32af89fa2be | ### Baseline-PS Accuracy: 0.9643. Result ID: 69f0737047f34ce924d66dbb. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"XLMR-large","Input Language":"en"}. This record does not assert independent reproduction. ### Tpl-rand-k Accuracy: 0.6518. Result ID: 69933f7c3a6c31484914af95. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evaluation protocol":"translate-train","Supervision type":"hard prompt labels","Data selection strategy":"rand-k"}. This record does not assert independent reproduction. ### Tpl-div-k Accuracy: 0.6501. Result ID: 69933f7c3a6c31484914af96. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evaluation protocol":"translate-train","Supervision type":"hard prompt labels","Data selection strategy":"div-k"}. This record does not assert independent reproduction. ### T-div-k Accuracy: 0.6487. Result ID: 69933f7c3a6c31484914af93. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evaluation protocol":"translate-train","Supervision type":"teacher soft pseudolabels","Data selection strategy":"div-k"}. This record does not assert independent reproduction. ### SRC+GEN Accuracy: 0.6464. Result ID: 69933f7c3a6c31484914af90. [Reporting paper]() Recorded evaluation configuration: {"Evaluation protocol":"translate-train"}. This record does not assert independent reproduction. ### Tpl-top-k Accuracy: 0.6406. Result ID: 69933f7c3a6c31484914af94. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evaluation protocol":"translate-train","Supervision type":"hard prompt labels","Data selection strategy":"top-k"}. This record does not assert independent reproduction. ### SRC+GEN Accuracy: 0.6381. Result ID: 69933f7c3a6c31484914af36. [Reporting paper]() Recorded evaluation configuration: {"Zero-shot":"true"}. This record does not assert independent reproduction. ### T-top-k Accuracy: 0.6345. Result ID: 69933f7c3a6c31484914af91. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evaluation protocol":"translate-train","Supervision type":"teacher soft pseudolabels","Data selection strategy":"top-k"}. This record does not assert independent reproduction. ### Tpl-rand-k Accuracy: 0.6329. Result ID: 69933f7c3a6c31484914af3b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"selection strategy":"rand-k","Zero-shot":"true"}. This record does not assert independent reproduction. ### Tpl-div-k Accuracy: 0.6227. Result ID: 69933f7c3a6c31484914af3c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"selection strategy":"div-k","Zero-shot":"true"}. This record does not assert independent reproduction. ### T-top-k Accuracy: 0.6202. Result ID: 69933f7c3a6c31484914af37. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"selection strategy":"top-k","Zero-shot":"true"}. This record does not assert independent reproduction. ### T-rand-k Accuracy: 0.6186. Result ID: 69933f7c3a6c31484914af92. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evaluation protocol":"translate-train","Supervision type":"teacher soft pseudolabels","Data selection strategy":"rand-k"}. This record does not assert independent reproduction. ### Tpl-top-k Accuracy: 0.6173. Result ID: 69933f7c3a6c31484914af3a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"selection strategy":"top-k","Zero-shot":"true"}. This record does not assert independent reproduction. ### SRC Accuracy: 0.6134. Result ID: 69933f7c3a6c31484914af8f. [Reporting paper]() Recorded evaluation configuration: {"Evaluation protocol":"translate-train"}. This record does not assert independent reproduction. ### Skyline Accuracy: 0.612. Result ID: 69f0737047f34ce924d66db8. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"XLMR-large","Input Language":"ur"}. This record does not assert independent reproduction. ### T-div-k Accuracy: 0.6103. Result ID: 69933f7c3a6c31484914af39. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"selection strategy":"div-k","Zero-shot":"true"}. This record does not assert independent reproduction. ### T-rand-k Accuracy: 0.5821. Result ID: 69933f7c3a6c31484914af38. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"selection strategy":"rand-k","Zero-shot":"true"}. This record does not assert independent reproduction. ### GEN Accuracy: 0.5735. Result ID: 69933f7c3a6c31484914af8e. [Reporting paper]() Recorded evaluation configuration: {"Evaluation protocol":"translate-train"}. This record does not assert independent reproduction. ### GEN Accuracy: 0.5659. Result ID: 69933f7c3a6c31484914af34. [Reporting paper]() Recorded evaluation configuration: {"Zero-shot":"true"}. This record does not assert independent reproduction. ### SRC Accuracy: 0.5543. Result ID: 69933f7c3a6c31484914af35. [Reporting paper]() Recorded evaluation configuration: {"Zero-shot":"true"}. This record does not assert independent reproduction. ### XITE-reg-reg Accuracy: 0.4992. Result ID: 69f0737047f34ce924d66dbd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"XLMR-large","Input Language":"en"}. This record does not assert independent reproduction. ### XITE-reg-lda Accuracy: 0.47. Result ID: 69f0737047f34ce924d66dbe. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"XLMR-large","Input Language":"ur"}. This record does not assert independent reproduction. ### XITE-reg-lda Accuracy: 0.3695. Result ID: 69f0737047f34ce924d66dbf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"XLMR-large","Input Language":"en"}. This record does not assert independent reproduction. ### XITE-reg-reg Accuracy: 0.344. Result ID: 69f0737047f34ce924d66dbc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"XLMR-large","Input Language":"ur"}. This record does not assert independent reproduction. ### Skyline Accuracy: 0.3347. Result ID: 69f0737047f34ce924d66db9. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"XLMR-large","Input Language":"en"}. This record does not assert independent reproduction. ### Baseline-PS Accuracy: 0.316. Result ID: 69f0737047f34ce924d66dba. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"XLMR-large","Input Language":"ur"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.