# Argument Facet Similarity on AFS (10-fold Cross-Validation)

Source: [Argument Facet Similarity on AFS (10-fold Cross-Validation)](<https://www.sota2.com/research/sota/argument-facet-similarity-on-afs-10-fold-cross-validation>)

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

Data updated: 2026-02-26T05:57:43.078Z

Evaluation of Argument Facet Similarity performance on the AFS dataset using 10-fold cross-validation, typically measured using Pearson correlation and Spearman rank correlation.

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 Facet Similarity |
| Dataset (including any stated split) | Argument Facet Similarity (AFS) (10-fold Cross-Validation) |
| Metric | Pearson Correlation Coefficient |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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

- [Pearson Correlation Coefficient](<https://www.sota2.com/research/sota/argument-facet-similarity-on-afs-10-fold-cross-validation.md?metric=Pearson%20Correlation%20Coefficient>): Higher is better; unit: PERCENT.

- [Spearman Rank Correlation Coefficient](<https://www.sota2.com/research/sota/argument-facet-similarity-on-afs-10-fold-cross-validation.md?metric=Spearman%20Rank%20Correlation%20Coefficient>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Pearson Correlation Coefficient | Result date | Report paper |
| --- | --- | --- | --- |
| BERT-AFS-large | 78.68 | Not recorded | 68fa66441e209131cea0f5ab |
| SBERT-AFS-large | 77.85 | Not recorded | 68fa66441e209131cea0f5ab |
| BERT-AFS-base | 77.2 | Not recorded | 68fa66441e209131cea0f5ab |
| SBERT-AFS-base | 76.57 | Not recorded | 68fa66441e209131cea0f5ab |
| SVR | 63.33 | Not recorded | 68fa66441e209131cea0f5ab |
| tf-idf | 46.77 | Not recorded | 68fa66441e209131cea0f5ab |
| Avg. GloVe embeddings | 32.4 | Not recorded | 68fa66441e209131cea0f5ab |
| InferSent - GloVe | 27.08 | Not recorded | 68fa66441e209131cea0f5ab |

### BERT-AFS-large

Pearson Correlation Coefficient: 78.68. Result ID: 698ce7f48b517eb4331d9701.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa65c31e209131cea0c4ed.md>)

[Implementation](<https://github.com/google-research/bert>)

Recorded evaluation configuration: {"Evaluation Protocol":"10-fold Cross-Validation","Backbone Size":"large"}. This record does not assert independent reproduction.

### SBERT-AFS-large

Pearson Correlation Coefficient: 77.85. Result ID: 698ce7f48b517eb4331d9702.

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

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

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

Recorded evaluation configuration: {"Evaluation Protocol":"10-fold Cross-Validation","Backbone Size":"large"}. This record does not assert independent reproduction.

### BERT-AFS-base

Pearson Correlation Coefficient: 77.2. Result ID: 698ce7f48b517eb4331d96ff.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa65c31e209131cea0c4ed.md>)

[Implementation](<https://github.com/google-research/bert>)

Recorded evaluation configuration: {"Evaluation Protocol":"10-fold Cross-Validation","Backbone Size":"base"}. This record does not assert independent reproduction.

### SBERT-AFS-base

Pearson Correlation Coefficient: 76.57. Result ID: 698ce7f48b517eb4331d9700.

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

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

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

Recorded evaluation configuration: {"Evaluation Protocol":"10-fold Cross-Validation","Backbone Size":"base"}. This record does not assert independent reproduction.

### SVR

Pearson Correlation Coefficient: 63.33. Result ID: 698ce7f48b517eb4331d96fe.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa63f21e209131cea01bb4.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"10-fold Cross-Validation"}. This record does not assert independent reproduction.

### tf-idf

Pearson Correlation Coefficient: 46.77. Result ID: 698ce7f48b517eb4331d96fb.

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

Recorded evaluation configuration: {"Model Type":"Unsupervised"}. This record does not assert independent reproduction.

### Avg. GloVe embeddings

Pearson Correlation Coefficient: 32.4. Result ID: 698ce7f48b517eb4331d96fc.

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

Recorded evaluation configuration: {"Model Type":"Unsupervised"}. This record does not assert independent reproduction.

### InferSent - GloVe

Pearson Correlation Coefficient: 27.08. Result ID: 698ce7f48b517eb4331d96fd.

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

Recorded evaluation configuration: {"Model Type":"Unsupervised"}. This record does not assert independent reproduction.

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