# Meta-review generation on Meta-Review Generation (test)

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

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

Data updated: 2026-02-26T05:45:37.207Z

Evaluation of models generating meta-reviews, typically assessed using ROUGE scores alongside specialized metrics like FusionEval and FacetEval.

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-Review Generation (test) |
| Metric | FusionEval |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 16 of 16 |
| 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

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

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

- [ROUGE-1](<https://www.sota2.com/research/sota/meta-review-generation-on-meta-review-generation-test.md?metric=ROUGE-1>): Higher is better; unit: PERCENT.

- [ROUGE-2](<https://www.sota2.com/research/sota/meta-review-generation-on-meta-review-generation-test.md?metric=ROUGE-2>): Higher is better; unit: PERCENT.

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

## Recorded results

| Method | FusionEval | Result date | Report paper |
| --- | --- | --- | --- |
| Pipeline-Ours | 57.43 | Not recorded | 68fa73771e209131cea5cb72 |
| Pipeline-Ours | 55.96 | Not recorded | 68fa73771e209131cea5cb72 |
| Prompt-Ours | 53.62 | Not recorded | 68fa73771e209131cea5cb72 |
| Pipeline-Ours | 52.8 | Not recorded | 68fa73771e209131cea5cb72 |
| Pipeline-Ours | 52.68 | Not recorded | 68fa73771e209131cea5cb72 |
| Prompt-Ours | 51.4 | Not recorded | 68fa73771e209131cea5cb72 |
| Prompt-Ours | 50.24 | Not recorded | 68fa73771e209131cea5cb72 |
| Prompt-Ours | 50.18 | Not recorded | 68fa73771e209131cea5cb72 |
| Prompt-Naive | 50.14 | Not recorded | 68fa73771e209131cea5cb72 |
| Prompt-LLM | 49.66 | Not recorded | 68fa73771e209131cea5cb72 |
| Prompt-LLM | 48.9 | Not recorded | 68fa73771e209131cea5cb72 |
| Prompt-LLM | 48.53 | Not recorded | 68fa73771e209131cea5cb72 |
| Prompt-Naive | 48.35 | Not recorded | 68fa73771e209131cea5cb72 |
| Prompt-Naive | 47.35 | Not recorded | 68fa73771e209131cea5cb72 |
| Prompt-Naive | 46.85 | Not recorded | 68fa73771e209131cea5cb72 |
| Prompt-LLM | 46.83 | Not recorded | 68fa73771e209131cea5cb72 |

### Pipeline-Ours

FusionEval: 57.43. Result ID: 6992eeea3a6c31484912758f.

[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: {"Backbone LLM":"GPT-4"}. This record does not assert independent reproduction.

### Pipeline-Ours

FusionEval: 55.96. Result ID: 6992eeea3a6c314849127593.

[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: {"Backbone LLM":"GPT-3.5"}. This record does not assert independent reproduction.

### Prompt-Ours

FusionEval: 53.62. Result ID: 6992eeea3a6c31484912758e.

[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: {"Backbone LLM":"GPT-4"}. This record does not assert independent reproduction.

### Pipeline-Ours

FusionEval: 52.8. Result ID: 6992eeea3a6c31484912759b.

[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: {"Backbone LLM":"LLaMA2-70B"}. This record does not assert independent reproduction.

### Pipeline-Ours

FusionEval: 52.68. Result ID: 6992eeea3a6c314849127597.

[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: {"Backbone LLM":"LLaMA2-7B"}. This record does not assert independent reproduction.

### Prompt-Ours

FusionEval: 51.4. Result ID: 6992eeea3a6c314849127592.

[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: {"Backbone LLM":"GPT-3.5"}. This record does not assert independent reproduction.

### Prompt-Ours

FusionEval: 50.24. Result ID: 6992eeea3a6c31484912759a.

[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: {"Backbone LLM":"LLaMA2-70B"}. This record does not assert independent reproduction.

### Prompt-Ours

FusionEval: 50.18. Result ID: 6992eeea3a6c314849127596.

[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: {"Backbone LLM":"LLaMA2-7B"}. This record does not assert independent reproduction.

### Prompt-Naive

FusionEval: 50.14. Result ID: 6992eeea3a6c31484912758c.

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

Recorded evaluation configuration: {"Backbone LLM":"GPT-4"}. This record does not assert independent reproduction.

### Prompt-LLM

FusionEval: 49.66. Result ID: 6992eeea3a6c314849127591.

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

Recorded evaluation configuration: {"Backbone LLM":"GPT-3.5"}. This record does not assert independent reproduction.

### Prompt-LLM

FusionEval: 48.9. Result ID: 6992eeea3a6c31484912758d.

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

Recorded evaluation configuration: {"Backbone LLM":"GPT-4"}. This record does not assert independent reproduction.

### Prompt-LLM

FusionEval: 48.53. Result ID: 6992eeea3a6c314849127599.

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

Recorded evaluation configuration: {"Backbone LLM":"LLaMA2-70B"}. This record does not assert independent reproduction.

### Prompt-Naive

FusionEval: 48.35. Result ID: 6992eeea3a6c314849127590.

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

Recorded evaluation configuration: {"Backbone LLM":"GPT-3.5"}. This record does not assert independent reproduction.

### Prompt-Naive

FusionEval: 47.35. Result ID: 6992eeea3a6c314849127598.

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

Recorded evaluation configuration: {"Backbone LLM":"LLaMA2-70B"}. This record does not assert independent reproduction.

### Prompt-Naive

FusionEval: 46.85. Result ID: 6992eeea3a6c314849127594.

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

Recorded evaluation configuration: {"Backbone LLM":"LLaMA2-7B"}. This record does not assert independent reproduction.

### Prompt-LLM

FusionEval: 46.83. Result ID: 6992eeea3a6c314849127595.

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

Recorded evaluation configuration: {"Backbone LLM":"LLaMA2-7B"}. This record does not assert independent reproduction.

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