# Natural Language Inference on XNLI Hi (test)

Source: [Natural Language Inference on XNLI Hi (test)](<https://www.sota2.com/research/sota/natural-language-inference-on-xnli-hi-test>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T05:29:53.405Z

Evaluation of cross-lingual Natural Language Inference performance specifically on the Hindi 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 Hi (test) |
| Metric | Accuracy |
| 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

- [Accuracy](<https://www.sota2.com/research/sota/natural-language-inference-on-xnli-hi-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| T-div-k | 71.65 | Not recorded | 68fa74281e209131cea6014e |
| T-top-k | 71.41 | Not recorded | 68fa74281e209131cea6014e |
| Tpl-rand-k | 71.19 | Not recorded | 68fa74281e209131cea6014e |
| T-rand-k | 71.12 | Not recorded | 68fa74281e209131cea6014e |
| Tpl-rand-k | 71.12 | Not recorded | 68fa74281e209131cea6014e |
| Tpl-div-k | 70.88 | Not recorded | 68fa74281e209131cea6014e |
| Tpl-top-k | 70.39 | Not recorded | 68fa74281e209131cea6014e |
| SRC+GEN | 70.2 | Not recorded | 68fa74281e209131cea6014e |
| Tpl-div-k | 69.89 | Not recorded | 68fa74281e209131cea6014e |
| Tpl-top-k | 69.86 | Not recorded | 68fa74281e209131cea6014e |
| T-top-k | 69.81 | Not recorded | 68fa74281e209131cea6014e |
| T-div-k | 69.65 | Not recorded | 68fa74281e209131cea6014e |
| SRC+GEN | 69.29 | Not recorded | 68fa74281e209131cea6014e |
| SRC | 67.72 | Not recorded | 68fa74281e209131cea6014e |
| T-rand-k | 67.68 | Not recorded | 68fa74281e209131cea6014e |
| SRC | 64.61 | Not recorded | 68fa74281e209131cea6014e |
| GEN | 62.06 | Not recorded | 68fa74281e209131cea6014e |
| GEN | 60.66 | Not recorded | 68fa74281e209131cea6014e |

### T-div-k

Accuracy: 71.65. Result ID: 69933f7c3a6c31484914af81.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74281e209131cea6014e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74281e209131cea6014e.md>)

[Implementation](<https://github.com/LLM-Based-Augmentations>)

Recorded evaluation configuration: {"Evaluation protocol":"translate-train","Supervision type":"teacher soft pseudolabels","Data selection strategy":"div-k"}. This record does not assert independent reproduction.

### T-top-k

Accuracy: 71.41. Result ID: 69933f7c3a6c31484914af7f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74281e209131cea6014e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74281e209131cea6014e.md>)

[Implementation](<https://github.com/LLM-Based-Augmentations>)

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: 71.19. Result ID: 69933f7b3a6c31484914af29.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74281e209131cea6014e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74281e209131cea6014e.md>)

[Implementation](<https://github.com/LLM-Based-Augmentations>)

Recorded evaluation configuration: {"selection strategy":"rand-k","Zero-shot":"true"}. This record does not assert independent reproduction.

### T-rand-k

Accuracy: 71.12. Result ID: 69933f7c3a6c31484914af80.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74281e209131cea6014e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74281e209131cea6014e.md>)

[Implementation](<https://github.com/LLM-Based-Augmentations>)

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-rand-k

Accuracy: 71.12. Result ID: 69933f7c3a6c31484914af83.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74281e209131cea6014e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74281e209131cea6014e.md>)

[Implementation](<https://github.com/LLM-Based-Augmentations>)

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: 70.88. Result ID: 69933f7c3a6c31484914af84.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74281e209131cea6014e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74281e209131cea6014e.md>)

[Implementation](<https://github.com/LLM-Based-Augmentations>)

Recorded evaluation configuration: {"Evaluation protocol":"translate-train","Supervision type":"hard prompt labels","Data selection strategy":"div-k"}. This record does not assert independent reproduction.

### Tpl-top-k

Accuracy: 70.39. Result ID: 69933f7c3a6c31484914af82.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74281e209131cea6014e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74281e209131cea6014e.md>)

[Implementation](<https://github.com/LLM-Based-Augmentations>)

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: 70.2. Result ID: 69933f7b3a6c31484914af24.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74281e209131cea6014e.md>)

Recorded evaluation configuration: {"Zero-shot":"true"}. This record does not assert independent reproduction.

### Tpl-div-k

Accuracy: 69.89. Result ID: 69933f7c3a6c31484914af2a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74281e209131cea6014e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74281e209131cea6014e.md>)

[Implementation](<https://github.com/LLM-Based-Augmentations>)

Recorded evaluation configuration: {"selection strategy":"div-k","Zero-shot":"true"}. This record does not assert independent reproduction.

### Tpl-top-k

Accuracy: 69.86. Result ID: 69933f7b3a6c31484914af28.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74281e209131cea6014e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74281e209131cea6014e.md>)

[Implementation](<https://github.com/LLM-Based-Augmentations>)

Recorded evaluation configuration: {"selection strategy":"top-k","Zero-shot":"true"}. This record does not assert independent reproduction.

### T-top-k

Accuracy: 69.81. Result ID: 69933f7b3a6c31484914af25.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74281e209131cea6014e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74281e209131cea6014e.md>)

[Implementation](<https://github.com/LLM-Based-Augmentations>)

Recorded evaluation configuration: {"selection strategy":"top-k","Zero-shot":"true"}. This record does not assert independent reproduction.

### T-div-k

Accuracy: 69.65. Result ID: 69933f7b3a6c31484914af27.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74281e209131cea6014e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74281e209131cea6014e.md>)

[Implementation](<https://github.com/LLM-Based-Augmentations>)

Recorded evaluation configuration: {"selection strategy":"div-k","Zero-shot":"true"}. This record does not assert independent reproduction.

### SRC+GEN

Accuracy: 69.29. Result ID: 69933f7c3a6c31484914af7e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74281e209131cea6014e.md>)

Recorded evaluation configuration: {"Evaluation protocol":"translate-train"}. This record does not assert independent reproduction.

### SRC

Accuracy: 67.72. Result ID: 69933f7c3a6c31484914af7d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74281e209131cea6014e.md>)

Recorded evaluation configuration: {"Evaluation protocol":"translate-train"}. This record does not assert independent reproduction.

### T-rand-k

Accuracy: 67.68. Result ID: 69933f7b3a6c31484914af26.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74281e209131cea6014e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74281e209131cea6014e.md>)

[Implementation](<https://github.com/LLM-Based-Augmentations>)

Recorded evaluation configuration: {"selection strategy":"rand-k","Zero-shot":"true"}. This record does not assert independent reproduction.

### SRC

Accuracy: 64.61. Result ID: 69933f7b3a6c31484914af23.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74281e209131cea6014e.md>)

Recorded evaluation configuration: {"Zero-shot":"true"}. This record does not assert independent reproduction.

### GEN

Accuracy: 62.06. Result ID: 69933f7b3a6c31484914af22.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74281e209131cea6014e.md>)

Recorded evaluation configuration: {"Zero-shot":"true"}. This record does not assert independent reproduction.

### GEN

Accuracy: 60.66. Result ID: 69933f7c3a6c31484914af7c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74281e209131cea6014e.md>)

Recorded evaluation configuration: {"Evaluation protocol":"translate-train"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.