# Language Modeling on Xinhua News (val)

Source: [Language Modeling on Xinhua News (val)](<https://www.sota2.com/research/sota/language-modeling-on-xinhua-news-val>)

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

Data updated: 2026-02-26T05:55:11.601Z

Evaluation of language modeling performance on the validation split of the Xinhua News dataset, typically measured using Perplexity (PPL) variants.

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 | Language Modeling |
| Dataset (including any stated split) | Xinhua News (val) |
| Metric | PPL (All) |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 3 of 3 |
| 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

- [PPL (All)](<https://www.sota2.com/research/sota/language-modeling-on-xinhua-news-val.md?metric=PPL%20(All)>): Lower is better; unit: SCALAR.

- [PPL (Entity)](<https://www.sota2.com/research/sota/language-modeling-on-xinhua-news-val.md?metric=PPL%20(Entity)>): Lower is better; unit: SCALAR.

- [PPL (Word)](<https://www.sota2.com/research/sota/language-modeling-on-xinhua-news-val.md?metric=PPL%20(Word)>): Lower is better; unit: SCALAR.

## Recorded results

| Method | PPL (All) | Result date | Report paper |
| --- | --- | --- | --- |
| Pointer | 30.43 | Not recorded | 68fa63871e209131ce9ff41e |
| Pointer | 32.57 | Not recorded | 68fa63871e209131ce9ff41e |
| LM | 33.08 | Not recorded | 68fa63871e209131ce9ff41e |

### Pointer

PPL (All): 30.43. Result ID: 698bf86df729bc7f68e70e30.

[Reporting paper](<https://www.sota2.com/research/paper/68fa63871e209131ce9ff41e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63871e209131ce9ff41e.md>)

Recorded evaluation configuration: {"initialization":"LM weights"}. This record does not assert independent reproduction.

### Pointer

PPL (All): 32.57. Result ID: 698bf86df729bc7f68e70e2f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa63871e209131ce9ff41e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63871e209131ce9ff41e.md>)

Recorded evaluation configuration: {"initialization":"random"}. This record does not assert independent reproduction.

### LM

PPL (All): 33.08. Result ID: 698bf86df729bc7f68e70e2e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa63871e209131ce9ff41e.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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