# Meta-review generation on Meta-reviews

Source: [Meta-review generation on Meta-reviews](<https://www.sota2.com/research/sota/meta-review-generation-on-meta-reviews>)

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

Data updated: 2026-02-26T05:58:56.866Z

Evaluation of model performance on generating meta-reviews using the Meta-reviews dataset, typically measured by Preferred rating and Inter-Annotator Agreement (IAA).

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 | Meta-review generation |
| Dataset (including any stated split) | Meta-reviews |
| Metric | Preferred Rate |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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

- [Preferred Rate](<https://www.sota2.com/research/sota/meta-review-generation-on-meta-reviews.md?metric=Preferred%20Rate>): Higher is better; unit: PERCENT.

- [IAA](<https://www.sota2.com/research/sota/meta-review-generation-on-meta-reviews.md?metric=IAA>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Preferred Rate | Result date | Report paper |
| --- | --- | --- | --- |
| Prompt-Ours | 73.33 | Not recorded | 68fa73771e209131cea5cb72 |
| Prompt-Ours | 53.33 | Not recorded | 68fa73771e209131cea5cb72 |
| Prompt-Naive | 46.67 | Not recorded | 68fa73771e209131cea5cb72 |
| Human-Written | 26.67 | Not recorded | 68fa73771e209131cea5cb72 |

### Prompt-Ours

Preferred Rate: 73.33. Result ID: 6992eeea3a6c31484912758a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73771e209131cea5cb72.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73771e209131cea5cb72.md>)

[Implementation](<https://github.com/oaimli/MetaReviewingLogic>)

Recorded evaluation configuration: {"LLM":"GPT-4","Competition Group":"vs. Human-Written"}. This record does not assert independent reproduction.

### Prompt-Ours

Preferred Rate: 53.33. Result ID: 6992eeea3a6c314849127589.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73771e209131cea5cb72.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73771e209131cea5cb72.md>)

[Implementation](<https://github.com/oaimli/MetaReviewingLogic>)

Recorded evaluation configuration: {"LLM":"LLaMA2-70B","Competition Group":"vs. Prompt-Naive LLaMA2-70B"}. This record does not assert independent reproduction.

### Prompt-Naive

Preferred Rate: 46.67. Result ID: 6992eeea3a6c314849127588.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73771e209131cea5cb72.md>)

Recorded evaluation configuration: {"LLM":"LLaMA2-70B","Competition Group":"vs. Prompt-Ours LLaMA2-70B"}. This record does not assert independent reproduction.

### Human-Written

Preferred Rate: 26.67. Result ID: 6992eeea3a6c31484912758b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73771e209131cea5cb72.md>)

Recorded evaluation configuration: {"Competition Group":"vs. Prompt-Ours GPT-4"}. This record does not assert independent reproduction.

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