# Text Generation on CommonGen

Source: [Text Generation on CommonGen](<https://www.sota2.com/research/sota/text-generation-on-commongen>)

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

Data updated: 2026-06-17T07:06:11.153Z

Evaluation of general text generation models on the CommonGen dataset, measured using metrics such as ROUGE-L.

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 |
| Dataset (including any stated split) | CommonGen |
| Metric | ROUGE-L |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 17 of 17 |
| 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-on-commongen.md?metric=ROUGE-L>): Higher is better; unit: PERCENT.

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

## Recorded results

| Method | ROUGE-L | Result date | Report paper |
| --- | --- | --- | --- |
| GENICL | 41 | Not recorded | 68fa78c21e209131cea7a598 |
| EPR | 39.2 | Not recorded | 68fa78c21e209131cea7a598 |
| ReLAR | 38.92 | Not recorded | 6a3229f4d33dfb23e783e9dc |
| BM25 | 38.3 | Not recorded | 68fa78c21e209131cea7a598 |
| SBERT | 37.8 | Not recorded | 68fa78c21e209131cea7a598 |
| E5base | 37.6 | Not recorded | 68fa78c21e209131cea7a598 |
| LLM-R | 37.2 | Not recorded | 68fa78c21e209131cea7a598 |
| Random | 36.3 | Not recorded | 68fa78c21e209131cea7a598 |
| Mistral-7B-Instruct | 35.67 | Not recorded | 6a3229f4d33dfb23e783e9dc |
| CBDS | 34.5 | Not recorded | 68fa78c21e209131cea7a598 |
| Llama-3-8B-Instruct | 33.94 | Not recorded | 6a3229f4d33dfb23e783e9dc |
| Qwen2.5-7B | 31.42 | Not recorded | 6a3229f4d33dfb23e783e9dc |
| Mistral-7B-v0.3 | 27.84 | Not recorded | 6a3229f4d33dfb23e783e9dc |
| Gemma-7B | 24.63 | Not recorded | 6a3229f4d33dfb23e783e9dc |
| LLaMA-2-7B | 21.37 | Not recorded | 6a3229f4d33dfb23e783e9dc |
| Falcon-7B | 19.28 | Not recorded | 6a3229f4d33dfb23e783e9dc |
| Zero-shot | 19.2 | Not recorded | 68fa78c21e209131cea7a598 |

### GENICL

ROUGE-L: 41. Result ID: 6995a11a3badfaffe69dccc3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78c21e209131cea7a598.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78c21e209131cea7a598.md>)

[Implementation](<https://foundation-model-research.github.io/GenICL>)

Recorded evaluation configuration: {"Backbone":"LLaMA-7B","Evaluation Setting":"Few-shot (ICL)"}. This record does not assert independent reproduction.

### EPR

ROUGE-L: 39.2. Result ID: 6995a11a3badfaffe69dccc1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78c21e209131cea7a598.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c781e209131cea341f3.md>)

Recorded evaluation configuration: {"Backbone":"LLaMA-7B","Evaluation Setting":"Few-shot (ICL)"}. This record does not assert independent reproduction.

### ReLAR

ROUGE-L: 38.92. Result ID: 6a32474bfbc373592c2f4bb1.

[Reporting paper](<https://www.sota2.com/research/paper/6a3229f4d33dfb23e783e9dc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a3229f4d33dfb23e783e9dc.md>)

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

### BM25

ROUGE-L: 38.3. Result ID: 6995a11a3badfaffe69dccbd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78c21e209131cea7a598.md>)

Recorded evaluation configuration: {"Backbone":"LLaMA-7B","Evaluation Setting":"Few-shot (ICL)"}. This record does not assert independent reproduction.

### SBERT

ROUGE-L: 37.8. Result ID: 6995a11a3badfaffe69dccbe.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78c21e209131cea7a598.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66441e209131cea0f5ab.md>)

[Implementation](<https://github.com/UKPLab/sentence-transformers>)

Recorded evaluation configuration: {"Backbone":"LLaMA-7B","Evaluation Setting":"Few-shot (ICL)"}. This record does not assert independent reproduction.

### E5base

ROUGE-L: 37.6. Result ID: 6995a11a3badfaffe69dccbf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78c21e209131cea7a598.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72491e209131cea5595a.md>)

[Implementation](<https://github.com/microsoft/unilm>)

Recorded evaluation configuration: {"Backbone":"LLaMA-7B","Evaluation Setting":"Few-shot (ICL)"}. This record does not assert independent reproduction.

### LLM-R

ROUGE-L: 37.2. Result ID: 6995a11a3badfaffe69dccc2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78c21e209131cea7a598.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71f21e209131cea53b15.md>)

Recorded evaluation configuration: {"Backbone":"LLaMA-7B","Evaluation Setting":"Few-shot (ICL)"}. This record does not assert independent reproduction.

### Random

ROUGE-L: 36.3. Result ID: 6995a11a3badfaffe69dccbc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78c21e209131cea7a598.md>)

Recorded evaluation configuration: {"Backbone":"LLaMA-7B","Evaluation Setting":"Few-shot (ICL)"}. This record does not assert independent reproduction.

### Mistral-7B-Instruct

ROUGE-L: 35.67. Result ID: 6a32474bfbc373592c2f4bae.

[Reporting paper](<https://www.sota2.com/research/paper/6a3229f4d33dfb23e783e9dc.md>)

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

### CBDS

ROUGE-L: 34.5. Result ID: 6995a11a3badfaffe69dccc0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78c21e209131cea7a598.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72211e209131cea54b16.md>)

[Implementation](<https://github.com/WANGXinyiLinda/concept-based-demonstration-selection>)

Recorded evaluation configuration: {"Backbone":"LLaMA-7B","Evaluation Setting":"Few-shot (ICL)"}. This record does not assert independent reproduction.

### Llama-3-8B-Instruct

ROUGE-L: 33.94. Result ID: 6a32474bfbc373592c2f4baf.

[Reporting paper](<https://www.sota2.com/research/paper/6a3229f4d33dfb23e783e9dc.md>)

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

### Qwen2.5-7B

ROUGE-L: 31.42. Result ID: 6a32474bfbc373592c2f4bad.

[Reporting paper](<https://www.sota2.com/research/paper/6a3229f4d33dfb23e783e9dc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa767e1e209131cea6d6a7.md>)

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

### Mistral-7B-v0.3

ROUGE-L: 27.84. Result ID: 6a32474bfbc373592c2f4bab.

[Reporting paper](<https://www.sota2.com/research/paper/6a3229f4d33dfb23e783e9dc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70d61e209131cea4d909.md>)

[Implementation](<https://github.com/mistralai/mistral-src>)

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

### Gemma-7B

ROUGE-L: 24.63. Result ID: 6a32474bfbc373592c2f4bac.

[Reporting paper](<https://www.sota2.com/research/paper/6a3229f4d33dfb23e783e9dc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72f11e209131cea5973c.md>)

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

### LLaMA-2-7B

ROUGE-L: 21.37. Result ID: 6a32474bfbc373592c2f4baa.

[Reporting paper](<https://www.sota2.com/research/paper/6a3229f4d33dfb23e783e9dc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa701f1e209131cea492fe.md>)

[Implementation](<https://github.com/facebookresearch/llama>)

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

### Falcon-7B

ROUGE-L: 19.28. Result ID: 6a32474bfbc373592c2f4bb0.

[Reporting paper](<https://www.sota2.com/research/paper/6a3229f4d33dfb23e783e9dc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa715b1e209131cea50cd0.md>)

[Implementation](<https://huggingface.co/tiiuae/>)

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

### Zero-shot

ROUGE-L: 19.2. Result ID: 6995a11a3badfaffe69dccbb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78c21e209131cea7a598.md>)

Recorded evaluation configuration: {"Backbone":"LLaMA-7B","Evaluation Setting":"Zero-shot"}. This record does not assert independent reproduction.

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