# Argument Generation on ArgGen

Source: [Argument Generation on ArgGen](<https://www.sota2.com/research/sota/argument-generation-on-arggen>)

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

Data updated: 2026-02-26T05:37:16.429Z

Evaluation of model performance on the Argument Generation task using the ArgGen dataset, typically measured using standard generation metrics like BLEU, ROUGE, and METEOR.

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 | Argument Generation |
| Dataset (including any stated split) | ArgGen |
| Metric | BLEU-2 |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 9 of 9 |
| 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

- [BLEU-2](<https://www.sota2.com/research/sota/argument-generation-on-arggen.md?metric=BLEU-2>): Higher is better; unit: SCALAR.

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

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

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

## Recorded results

| Method | BLEU-2 | Result date | Report paper |
| --- | --- | --- | --- |
| PLANET | 38.55 | Not recorded | 68fa6c0e1e209131cea31c91 |
| PLANET w/o CL | 38.39 | Not recorded | 68fa6c0e1e209131cea31c91 |
| PLANET w/o CL - BOW | 37.9 | Not recorded | 68fa6c0e1e209131cea31c91 |
| PLANET w/o CL - SEL. | 37.66 | Not recorded | 68fa6c0e1e209131cea31c91 |
| SSPLANER | 36.92 | Not recorded | 68fa6c0e1e209131cea31c91 |
| FULLSEQ2SEQ | 36.69 | Not recorded | 68fa6c0e1e209131cea31c91 |
| SEPPLAN | 32.38 | Not recorded | 68fa6c0e1e209131cea31c91 |
| HIERPLAN | 14.29 | Not recorded | 68fa6c0e1e209131cea31c91 |
| RETRIEVAL | 10.95 | Not recorded | 68fa6c0e1e209131cea31c91 |

### PLANET

BLEU-2: 38.55. Result ID: 698ec135ffc3901de0a0c739.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c0e1e209131cea31c91.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c0e1e209131cea31c91.md>)

Recorded evaluation configuration: {"contrastive loss":"on"}. This record does not assert independent reproduction.

### PLANET w/o CL

BLEU-2: 38.39. Result ID: 698ec135ffc3901de0a0c736.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c0e1e209131cea31c91.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c0e1e209131cea31c91.md>)

Recorded evaluation configuration: {"contrastive loss":"off"}. This record does not assert independent reproduction.

### PLANET w/o CL - BOW

BLEU-2: 37.9. Result ID: 698ec135ffc3901de0a0c738.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c0e1e209131cea31c91.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c0e1e209131cea31c91.md>)

Recorded evaluation configuration: {"contrastive loss":"off","bag-of-words planning":"off"}. This record does not assert independent reproduction.

### PLANET w/o CL - SEL.

BLEU-2: 37.66. Result ID: 698ec135ffc3901de0a0c737.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c0e1e209131cea31c91.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c0e1e209131cea31c91.md>)

Recorded evaluation configuration: {"contrastive loss":"off","content selection":"off"}. This record does not assert independent reproduction.

### SSPLANER

BLEU-2: 36.92. Result ID: 698ec135ffc3901de0a0c735.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c0e1e209131cea31c91.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68851e209131cea1cab3.md>)

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

### FULLSEQ2SEQ

BLEU-2: 36.69. Result ID: 698ec135ffc3901de0a0c733.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c0e1e209131cea31c91.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67751e209131cea1672c.md>)

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

### SEPPLAN

BLEU-2: 32.38. Result ID: 698ec135ffc3901de0a0c734.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c0e1e209131cea31c91.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa686b1e209131cea1c051.md>)

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

### HIERPLAN

BLEU-2: 14.29. Result ID: 698ec135ffc3901de0a0c732.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c0e1e209131cea31c91.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65e01e209131cea0d144.md>)

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

### RETRIEVAL

BLEU-2: 10.95. Result ID: 698ec135ffc3901de0a0c731.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c0e1e209131cea31c91.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.