# Slot Filling on MIT-R

Source: [Slot Filling on MIT-R](<https://www.sota2.com/research/sota/slot-filling-on-mit-r>)

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

Data updated: 2026-02-26T05:27:51.534Z

Evaluation of Slot Filling performance on the MIT-R dataset.

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 | Slot Filling |
| Dataset (including any stated split) | MIT-R |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 13 of 13 |
| 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

- [Accuracy](<https://www.sota2.com/research/sota/slot-filling-on-mit-r.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| ROBERTa-CL | 88.51 | Not recorded | 68fa699a1e209131cea23031 |
| COSINE | 76.61 | Not recorded | 68fa699a1e209131cea23031 |
| UST | 74.41 | Not recorded | 68fa699a1e209131cea23031 |
| ImplyLoss | 74.3 | Not recorded | 68fa699a1e209131cea23031 |
| Mixup | 73.68 | Not recorded | 68fa699a1e209131cea23031 |
| SMART | 73.66 | Not recorded | 68fa699a1e209131cea23031 |
| FreeLB | 73.04 | Not recorded | 68fa699a1e209131cea23031 |
| Init | 72.97 | Not recorded | 68fa699a1e209131cea23031 |
| Self-ensemble | 72.88 | Not recorded | 68fa699a1e209131cea23031 |
| ROBERTa-WL+ | 70.95 | Not recorded | 68fa699a1e209131cea23031 |
| Denoise | 70.58 | Not recorded | 68fa699a1e209131cea23031 |
| ExMatch | 34.93 | Not recorded | 68fa699a1e209131cea23031 |
| Snorkel | 20.63 | Not recorded | 68fa699a1e209131cea23031 |

### ROBERTa-CL

Accuracy: 88.51. Result ID: 698dc2e78b517eb4332390fb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa699a1e209131cea23031.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66131e209131cea0e18b.md>)

[Implementation](<https://github.com/pytorch/fairseq>)

Recorded evaluation configuration: {"Training supervision type":"clean labels","Method categorization":"Fully-supervised"}. This record does not assert independent reproduction.

### COSINE

Accuracy: 76.61. Result ID: 698dc2e78b517eb433239106.

[Reporting paper](<https://www.sota2.com/research/paper/68fa699a1e209131cea23031.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa699a1e209131cea23031.md>)

[Implementation](<https://github.com/yueyu1030/COSINE>)

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

### UST

Accuracy: 74.41. Result ID: 698dc2e78b517eb433239104.

[Reporting paper](<https://www.sota2.com/research/paper/68fa699a1e209131cea23031.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67d41e209131cea18c04.md>)

Recorded evaluation configuration: {"Method categorization":"Baseline"}. This record does not assert independent reproduction.

### ImplyLoss

Accuracy: 74.3. Result ID: 698dc2e78b517eb433239102.

[Reporting paper](<https://www.sota2.com/research/paper/68fa699a1e209131cea23031.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67881e209131cea16b6f.md>)

Recorded evaluation configuration: {"Method categorization":"Baseline"}. This record does not assert independent reproduction.

### Mixup

Accuracy: 73.68. Result ID: 698dc2e78b517eb4332390ff.

[Reporting paper](<https://www.sota2.com/research/paper/68fa699a1e209131cea23031.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa644e1e209131cea03e44.md>)

[Implementation](<https://github.com/facebookresearch/mixup-cifar10>)

Recorded evaluation configuration: {"Method categorization":"Baseline"}. This record does not assert independent reproduction.

### SMART

Accuracy: 73.66. Result ID: 698dc2e78b517eb433239100.

[Reporting paper](<https://www.sota2.com/research/paper/68fa699a1e209131cea23031.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa58711e209131ce9ae277.md>)

[Implementation](<https://github.com/namisan/mt-dnn>)

Recorded evaluation configuration: {"Method categorization":"Baseline"}. This record does not assert independent reproduction.

### FreeLB

Accuracy: 73.04. Result ID: 698dc2e78b517eb4332390fe.

[Reporting paper](<https://www.sota2.com/research/paper/68fa699a1e209131cea23031.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67711e209131cea164b2.md>)

Recorded evaluation configuration: {"Method categorization":"Baseline"}. This record does not assert independent reproduction.

### Init

Accuracy: 72.97. Result ID: 698dc2e78b517eb433239105.

[Reporting paper](<https://www.sota2.com/research/paper/68fa699a1e209131cea23031.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa699a1e209131cea23031.md>)

[Implementation](<https://github.com/yueyu1030/COSINE>)

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

### Self-ensemble

Accuracy: 72.88. Result ID: 698dc2e78b517eb4332390fd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa699a1e209131cea23031.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67181e209131cea141ad.md>)

Recorded evaluation configuration: {"Method categorization":"Baseline"}. This record does not assert independent reproduction.

### ROBERTa-WL+

Accuracy: 70.95. Result ID: 698dc2e78b517eb4332390fc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa699a1e209131cea23031.md>)

Recorded evaluation configuration: {"Training supervision type":"weak labels","Method categorization":"Baseline"}. This record does not assert independent reproduction.

### Denoise

Accuracy: 70.58. Result ID: 698dc2e78b517eb433239103.

[Reporting paper](<https://www.sota2.com/research/paper/68fa699a1e209131cea23031.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa697f1e209131cea2276d.md>)

Recorded evaluation configuration: {"Method categorization":"Baseline"}. This record does not assert independent reproduction.

### ExMatch

Accuracy: 34.93. Result ID: 698dc2e78b517eb4332390fa.

[Reporting paper](<https://www.sota2.com/research/paper/68fa699a1e209131cea23031.md>)

Recorded evaluation configuration: {"Method categorization":"Baseline"}. This record does not assert independent reproduction.

### Snorkel

Accuracy: 20.63. Result ID: 698dc2e78b517eb433239101.

[Reporting paper](<https://www.sota2.com/research/paper/68fa699a1e209131cea23031.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63d81e209131cea01392.md>)

Recorded evaluation configuration: {"Method categorization":"Baseline"}. This record does not assert independent reproduction.

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