# Multi-Aspect Controllable Text Generation on Fyelp CompMCTG (Hold-Out)

Source: [Multi-Aspect Controllable Text Generation on Fyelp CompMCTG (Hold-Out)](<https://www.sota2.com/research/sota/multi-aspect-controllable-text-generation-on-fyelp-compmctg-hold-out>)

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

Data updated: 2026-02-26T05:34:38.635Z

Evaluation of Multi-Aspect Controllable Text Generation performance on the hold-out split of the Fyelp CompMCTG dataset, focusing on aspect completeness (Acomp) and preference score (Pcomp).

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 | Multi-Aspect Controllable Text Generation |
| Dataset (including any stated split) | Fyelp CompMCTG (Hold-Out) |
| Metric | Acomp |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 12 of 12 |
| 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

- [Acomp](<https://www.sota2.com/research/sota/multi-aspect-controllable-text-generation-on-fyelp-compmctg-hold-out.md?metric=Acomp>): Higher is better; unit: PERCENT.

- [Preference Score](<https://www.sota2.com/research/sota/multi-aspect-controllable-text-generation-on-fyelp-compmctg-hold-out.md?metric=Preference%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Acomp | Result date | Report paper |
| --- | --- | --- | --- |
| Meta-Con.Prefix | 94.06 | Not recorded | 68fa73671e209131cea5c3a8 |
| Con. Prefix | 92.79 | Not recorded | 68fa73671e209131cea5c3a8 |
| Meta-CTRL | 83.85 | Not recorded | 68fa73671e209131cea5c3a8 |
| CTRL | 82.02 | Not recorded | 68fa73671e209131cea5c3a8 |
| Meta-DCG | 81.15 | Not recorded | 68fa73671e209131cea5c3a8 |
| DCG | 80.61 | Not recorded | 68fa73671e209131cea5c3a8 |
| Meta-CTRL | 68.69 | Not recorded | 68fa73671e209131cea5c3a8 |
| CTRL | 68.23 | Not recorded | 68fa73671e209131cea5c3a8 |
| Meta-Con.Prefix | 67.75 | Not recorded | 68fa73671e209131cea5c3a8 |
| Con. Prefix | 67.5 | Not recorded | 68fa73671e209131cea5c3a8 |
| DCG | 66.39 | Not recorded | 68fa73671e209131cea5c3a8 |
| Meta-DCG | 66.36 | Not recorded | 68fa73671e209131cea5c3a8 |

### Meta-Con.Prefix

Acomp: 94.06. Result ID: 6992c7293a6c314849116c9c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73671e209131cea5c3a8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73671e209131cea5c3a8.md>)

[Implementation](<https://github.com/tqzhong/CG4MCTG>)

Recorded evaluation configuration: {"Training Framework":"Meta-MCTG"}. This record does not assert independent reproduction.

### Con. Prefix

Acomp: 92.79. Result ID: 6992c7293a6c314849116c9b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73671e209131cea5c3a8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bdd1e209131cea30afd.md>)

Recorded evaluation configuration: {"Training Framework":"Standard"}. This record does not assert independent reproduction.

### Meta-CTRL

Acomp: 83.85. Result ID: 6992c7293a6c314849116c9a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73671e209131cea5c3a8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73671e209131cea5c3a8.md>)

[Implementation](<https://github.com/tqzhong/CG4MCTG>)

Recorded evaluation configuration: {"Training Framework":"Meta-MCTG"}. This record does not assert independent reproduction.

### CTRL

Acomp: 82.02. Result ID: 6992c7293a6c314849116c99.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73671e209131cea5c3a8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa665f1e209131cea0fe3b.md>)

Recorded evaluation configuration: {"Training Framework":"Standard"}. This record does not assert independent reproduction.

### Meta-DCG

Acomp: 81.15. Result ID: 6992c7293a6c314849116c9e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73671e209131cea5c3a8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73671e209131cea5c3a8.md>)

[Implementation](<https://github.com/tqzhong/CG4MCTG>)

Recorded evaluation configuration: {"Training Framework":"Meta-MCTG"}. This record does not assert independent reproduction.

### DCG

Acomp: 80.61. Result ID: 6992c7293a6c314849116c9d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73671e209131cea5c3a8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fcd1e209131cea47828.md>)

[Implementation](<https://github.com/Zeng-WH/Seen-to-Unseen.>)

Recorded evaluation configuration: {"Training Framework":"Standard"}. This record does not assert independent reproduction.

### Meta-CTRL

Acomp: 68.69. Result ID: 6992c7293a6c314849116c88.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73671e209131cea5c3a8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73671e209131cea5c3a8.md>)

[Implementation](<https://github.com/tqzhong/CG4MCTG>)

Recorded evaluation configuration: {"Training Framework":"Meta-MCTG"}. This record does not assert independent reproduction.

### CTRL

Acomp: 68.23. Result ID: 6992c7293a6c314849116c87.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73671e209131cea5c3a8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa665f1e209131cea0fe3b.md>)

Recorded evaluation configuration: {"Training Framework":"Standard"}. This record does not assert independent reproduction.

### Meta-Con.Prefix

Acomp: 67.75. Result ID: 6992c7293a6c314849116c8a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73671e209131cea5c3a8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73671e209131cea5c3a8.md>)

[Implementation](<https://github.com/tqzhong/CG4MCTG>)

Recorded evaluation configuration: {"Training Framework":"Meta-MCTG"}. This record does not assert independent reproduction.

### Con. Prefix

Acomp: 67.5. Result ID: 6992c7293a6c314849116c89.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73671e209131cea5c3a8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bdd1e209131cea30afd.md>)

Recorded evaluation configuration: {"Training Framework":"Standard"}. This record does not assert independent reproduction.

### DCG

Acomp: 66.39. Result ID: 6992c7293a6c314849116c8b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73671e209131cea5c3a8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fcd1e209131cea47828.md>)

[Implementation](<https://github.com/Zeng-WH/Seen-to-Unseen.>)

Recorded evaluation configuration: {"Training Framework":"Standard"}. This record does not assert independent reproduction.

### Meta-DCG

Acomp: 66.36. Result ID: 6992c7293a6c314849116c8c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73671e209131cea5c3a8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73671e209131cea5c3a8.md>)

[Implementation](<https://github.com/tqzhong/CG4MCTG>)

Recorded evaluation configuration: {"Training Framework":"Meta-MCTG"}. This record does not assert independent reproduction.

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