# Text Generation and Reranking on RJUA

Source: [Text Generation and Reranking on RJUA](<https://www.sota2.com/research/sota/text-generation-and-reranking-on-rjua>)

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

Data updated: 2026-05-28T08:11:42.918Z

Evaluation of text generation quality and reranking performance on the RJUA dataset, utilizing metrics such as Rouge-L, Reranker score, and rank-based metrics (RL@8, RR@8).

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 | Text Generation and Reranking |
| Dataset (including any stated split) | RJUA |
| Metric | Rouge-L |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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

- [Rouge-L](<https://www.sota2.com/research/sota/text-generation-and-reranking-on-rjua.md?metric=Rouge-L>): Higher is better; unit: PERCENT.

- [Reranker Score](<https://www.sota2.com/research/sota/text-generation-and-reranking-on-rjua.md?metric=Reranker%20Score>): Higher is better; unit: PERCENT.

- [RL@8](<https://www.sota2.com/research/sota/text-generation-and-reranking-on-rjua.md?metric=RL%408>): Higher is better; unit: PERCENT.

- [RR@8](<https://www.sota2.com/research/sota/text-generation-and-reranking-on-rjua.md?metric=RR%408>): Higher is better; unit: PERCENT.

- [Average Score](<https://www.sota2.com/research/sota/text-generation-and-reranking-on-rjua.md?metric=Average%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Rouge-L | Result date | Report paper |
| --- | --- | --- | --- |
| EAPO | 34.1 | Not recorded | 6a17cc2bdbd7150506f813f2 |
| W-REINFORCE | 33.6 | Not recorded | 6a17cc2bdbd7150506f813f2 |
| GRPO | 32.3 | Not recorded | 6a17cc2bdbd7150506f813f2 |
| PSR | 28.7 | Not recorded | 6a17cc2bdbd7150506f813f2 |
| NSR | 24.6 | Not recorded | 6a17cc2bdbd7150506f813f2 |

### EAPO

Rouge-L: 34.1. Result ID: 6a17f7d3fbc373592c119124.

[Reporting paper](<https://www.sota2.com/research/paper/6a17cc2bdbd7150506f813f2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a17cc2bdbd7150506f813f2.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction.

### W-REINFORCE

Rouge-L: 33.6. Result ID: 6a17f7d3fbc373592c119123.

[Reporting paper](<https://www.sota2.com/research/paper/6a17cc2bdbd7150506f813f2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79001e209131cea7b98b.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction.

### GRPO

Rouge-L: 32.3. Result ID: 6a17f7d3fbc373592c119120.

[Reporting paper](<https://www.sota2.com/research/paper/6a17cc2bdbd7150506f813f2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76a91e209131cea6e3eb.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction.

### PSR

Rouge-L: 28.7. Result ID: 6a17f7d3fbc373592c119121.

[Reporting paper](<https://www.sota2.com/research/paper/6a17cc2bdbd7150506f813f2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79001e209131cea7b98b.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction.

### NSR

Rouge-L: 24.6. Result ID: 6a17f7d3fbc373592c119122.

[Reporting paper](<https://www.sota2.com/research/paper/6a17cc2bdbd7150506f813f2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79001e209131cea7b98b.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction.

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