# Referring Description on RefCOCOg In-Domain

Source: [Referring Description on RefCOCOg In-Domain](<https://www.sota2.com/research/sota/referring-description-on-refcocog-in-domain>)

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

Data updated: 2026-02-27T14:24:07.557Z

Evaluation of Referring Description performance on the In-Domain subset of the RefCOCOg dataset, measured using standard language generation metrics (BLEU, METEOR, CIDEr, SPICE).

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 | Referring Description |
| Dataset (including any stated split) | RefCOCOg In-Domain |
| Metric | BLEU-4 |
| Unit | PERCENT |
| 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-4](<https://www.sota2.com/research/sota/referring-description-on-refcocog-in-domain.md?metric=BLEU-4>): Higher is better; unit: PERCENT.

- [METEOR](<https://www.sota2.com/research/sota/referring-description-on-refcocog-in-domain.md?metric=METEOR>): Higher is better; unit: PERCENT.

- [CIDEr](<https://www.sota2.com/research/sota/referring-description-on-refcocog-in-domain.md?metric=CIDEr>): Higher is better; unit: PERCENT.

- [SPICE](<https://www.sota2.com/research/sota/referring-description-on-refcocog-in-domain.md?metric=SPICE>): Higher is better; unit: PERCENT.

## Recorded results

| Method | BLEU-4 | Result date | Report paper |
| --- | --- | --- | --- |
| LLaVA-HR + ControlMLLM++ | 7.5 | Not recorded | 699d30c56017c4460ffab7ec |
| LLaVA-HR + ControlMLLM | 6.32 | Not recorded | 699d30c56017c4460ffab7ec |
| LLaVA-1.5 + ControlMLLM++ | 6.24 | Not recorded | 699d30c56017c4460ffab7ec |
| LLaVA-1.5 + ControlMLLM | 5.53 | Not recorded | 699d30c56017c4460ffab7ec |
| Qwen2.5-VL + ControlMLLM++ | 5.45 | Not recorded | 699d30c56017c4460ffab7ec |
| Qwen2.5-VL + ControlMLLM | 5.33 | Not recorded | 699d30c56017c4460ffab7ec |
| LLaVA-HR | 5.28 | Not recorded | 699d30c56017c4460ffab7ec |
| Qwen2.5-VL | 5.22 | Not recorded | 699d30c56017c4460ffab7ec |
| LLaVA-1.5 | 5.02 | Not recorded | 699d30c56017c4460ffab7ec |

### LLaVA-HR + ControlMLLM++

BLEU-4: 7.5. Result ID: 69a1a90535dfcabb00e81097.

[Reporting paper](<https://www.sota2.com/research/paper/699d30c56017c4460ffab7ec.md>)

[Method origin paper](<https://www.sota2.com/research/paper/699d30c56017c4460ffab7ec.md>)

Recorded evaluation configuration: {"Base Model":"LLaVA-HR","Enhanced with":"ControlMLLM++"}. This record does not assert independent reproduction.

### LLaVA-HR + ControlMLLM

BLEU-4: 6.32. Result ID: 69a1a90535dfcabb00e81096.

[Reporting paper](<https://www.sota2.com/research/paper/699d30c56017c4460ffab7ec.md>)

[Method origin paper](<https://www.sota2.com/research/paper/699d30c56017c4460ffab7ec.md>)

Recorded evaluation configuration: {"Base Model":"LLaVA-HR","Enhanced with":"ControlMLLM"}. This record does not assert independent reproduction.

### LLaVA-1.5 + ControlMLLM++

BLEU-4: 6.24. Result ID: 69a1a90535dfcabb00e81094.

[Reporting paper](<https://www.sota2.com/research/paper/699d30c56017c4460ffab7ec.md>)

[Method origin paper](<https://www.sota2.com/research/paper/699d30c56017c4460ffab7ec.md>)

Recorded evaluation configuration: {"Base Model":"LLaVA-1.5","Enhanced with":"ControlMLLM++"}. This record does not assert independent reproduction.

### LLaVA-1.5 + ControlMLLM

BLEU-4: 5.53. Result ID: 69a1a90535dfcabb00e81093.

[Reporting paper](<https://www.sota2.com/research/paper/699d30c56017c4460ffab7ec.md>)

[Method origin paper](<https://www.sota2.com/research/paper/699d30c56017c4460ffab7ec.md>)

Recorded evaluation configuration: {"Base Model":"LLaVA-1.5","Enhanced with":"ControlMLLM"}. This record does not assert independent reproduction.

### Qwen2.5-VL + ControlMLLM++

BLEU-4: 5.45. Result ID: 69a1a90535dfcabb00e8109a.

[Reporting paper](<https://www.sota2.com/research/paper/699d30c56017c4460ffab7ec.md>)

[Method origin paper](<https://www.sota2.com/research/paper/699d30c56017c4460ffab7ec.md>)

Recorded evaluation configuration: {"Base Model":"Qwen2.5-VL","Enhanced with":"ControlMLLM++"}. This record does not assert independent reproduction.

### Qwen2.5-VL + ControlMLLM

BLEU-4: 5.33. Result ID: 69a1a90535dfcabb00e81099.

[Reporting paper](<https://www.sota2.com/research/paper/699d30c56017c4460ffab7ec.md>)

[Method origin paper](<https://www.sota2.com/research/paper/699d30c56017c4460ffab7ec.md>)

Recorded evaluation configuration: {"Base Model":"Qwen2.5-VL","Enhanced with":"ControlMLLM"}. This record does not assert independent reproduction.

### LLaVA-HR

BLEU-4: 5.28. Result ID: 69a1a90535dfcabb00e81095.

[Reporting paper](<https://www.sota2.com/research/paper/699d30c56017c4460ffab7ec.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72621e209131cea56142.md>)

[Implementation](<https://github.com/luogen1996/LLaVA-HR>)

Recorded evaluation configuration: {"Base Model":"LLaVA-HR"}. This record does not assert independent reproduction.

### Qwen2.5-VL

BLEU-4: 5.22. Result ID: 69a1a90535dfcabb00e81098.

[Reporting paper](<https://www.sota2.com/research/paper/699d30c56017c4460ffab7ec.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa773a1e209131cea71d3c.md>)

Recorded evaluation configuration: {"Base Model":"Qwen2.5-VL"}. This record does not assert independent reproduction.

### LLaVA-1.5

BLEU-4: 5.02. Result ID: 69a1a90535dfcabb00e81092.

[Reporting paper](<https://www.sota2.com/research/paper/699d30c56017c4460ffab7ec.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa717d1e209131cea51970.md>)

[Implementation](<https://llava-vl.github.io/>)

Recorded evaluation configuration: {"Base Model":"LLaVA-1.5"}. This record does not assert independent reproduction.

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