# Learning to Explain on BeerAdvocate Appearance (test)

Source: [Learning to Explain on BeerAdvocate Appearance (test)](<https://www.sota2.com/research/sota/learning-to-explain-on-beeradvocate-appearance-test>)

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

Data updated: 2026-02-26T06:06:19.131Z

Evaluation of Learning to Explain performance on the test split of the BeerAdvocate Appearance dataset, measured using Test MSE and Subset Precision.

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 | Learning to Explain |
| Dataset (including any stated split) | BeerAdvocate Appearance (test) |
| Metric | Test MSE |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 3 of 3 |
| 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

- [Test MSE](<https://www.sota2.com/research/sota/learning-to-explain-on-beeradvocate-appearance-test.md?metric=Test%20MSE>): Lower is better; unit: SCALAR.

- [Subset Precision](<https://www.sota2.com/research/sota/learning-to-explain-on-beeradvocate-appearance-test.md?metric=Subset%20Precision>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Test MSE | Result date | Report paper |
| --- | --- | --- | --- |
| SoftSub | 2.48 | Not recorded | 68fa6b161e209131cea2c0e0 |
| I-MLE | 2.51 | Not recorded | 68fa6b161e209131cea2c0e0 |
| L2X | 10.7 | Not recorded | 68fa6b161e209131cea2c0e0 |

### SoftSub

Test MSE: 2.48. Result ID: 698e556fffc3901de09cb475.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b161e209131cea2c0e0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69571e209131cea21abf.md>)

Recorded evaluation configuration: {"tau":0.5,"k":10}. This record does not assert independent reproduction.

### I-MLE

Test MSE: 2.51. Result ID: 698e556fffc3901de09cb476.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b161e209131cea2c0e0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b161e209131cea2c0e0.md>)

[Implementation](<https://github.com/nec-research/tf-imle>)

Recorded evaluation configuration: {"tau":50,"k":10}. This record does not assert independent reproduction.

### L2X

Test MSE: 10.7. Result ID: 698e556fffc3901de09cb474.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b161e209131cea2c0e0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64821e209131cea04fd4.md>)

Recorded evaluation configuration: {"tau":0.1,"k":10}. This record does not assert independent reproduction.

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