# Poem Sentiment Analysis on PoemS (val)

Source: [Poem Sentiment Analysis on PoemS (val)](<https://www.sota2.com/research/sota/poem-sentiment-analysis-on-poems-val>)

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

Data updated: 2026-03-19T08:50:24.026Z

Evaluation of Poem Sentiment Analysis performance on the validation split of the PoemS dataset, measured using Accuracy and Expected Calibration Error (ECE).

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 | Poem Sentiment Analysis |
| Dataset (including any stated split) | PoemS (val) |
| Metric | Accuracy |
| 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

- [Accuracy](<https://www.sota2.com/research/sota/poem-sentiment-analysis-on-poems-val.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [ECE](<https://www.sota2.com/research/sota/poem-sentiment-analysis-on-poems-val.md?metric=ECE>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| IA2 → SFT | 68.4 | Not recorded | 68fa7bac1e209131cea89ce3 |
| ICL | 65.1 | Not recorded | 68fa7bac1e209131cea89ce3 |
| IA2 only | 62.4 | Not recorded | 68fa7bac1e209131cea89ce3 |
| IA2 → SFT | 60.6 | Not recorded | 68fa7bac1e209131cea89ce3 |
| ICL | 56.9 | Not recorded | 68fa7bac1e209131cea89ce3 |
| SFT only | 56.5 | Not recorded | 68fa7bac1e209131cea89ce3 |
| IA2 only | 52.8 | Not recorded | 68fa7bac1e209131cea89ce3 |
| SFT only | 49.9 | Not recorded | 68fa7bac1e209131cea89ce3 |

### IA2 → SFT

Accuracy: 68.4. Result ID: 69bbb8cd47f34ce924a5a9dd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bac1e209131cea89ce3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bac1e209131cea89ce3.md>)

Recorded evaluation configuration: {"Model":"Qwen3-4B-Base","N":"4","Source Dataset":"SST2","OOD":"true"}. This record does not assert independent reproduction.

### ICL

Accuracy: 65.1. Result ID: 69bbb8cd47f34ce924a5a9da.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bac1e209131cea89ce3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa680c1e209131cea19d53.md>)

[Implementation](<https://github.com/openai/gpt-3/blob/master/overlap_frequency.md>)

Recorded evaluation configuration: {"Model":"Qwen3-4B-Base","N":"4","Source Dataset":"SST2","OOD":"true"}. This record does not assert independent reproduction.

### IA2 only

Accuracy: 62.4. Result ID: 69bbb8cd47f34ce924a5a9dc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bac1e209131cea89ce3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bac1e209131cea89ce3.md>)

Recorded evaluation configuration: {"Model":"Qwen3-4B-Base","N":"4","Source Dataset":"SST2","OOD":"true"}. This record does not assert independent reproduction.

### IA2 → SFT

Accuracy: 60.6. Result ID: 69bbb8cd47f34ce924a5a9d9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bac1e209131cea89ce3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bac1e209131cea89ce3.md>)

Recorded evaluation configuration: {"Model":"Qwen3-4B-Base","N":"4","Source Dataset":"FinS","OOD":"true"}. This record does not assert independent reproduction.

### ICL

Accuracy: 56.9. Result ID: 69bbb8cd47f34ce924a5a9d6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bac1e209131cea89ce3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa680c1e209131cea19d53.md>)

[Implementation](<https://github.com/openai/gpt-3/blob/master/overlap_frequency.md>)

Recorded evaluation configuration: {"Model":"Qwen3-4B-Base","N":"4","Source Dataset":"FinS","OOD":"true"}. This record does not assert independent reproduction.

### SFT only

Accuracy: 56.5. Result ID: 69bbb8cd47f34ce924a5a9db.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bac1e209131cea89ce3.md>)

Recorded evaluation configuration: {"Model":"Qwen3-4B-Base","N":"4","Source Dataset":"SST2","OOD":"true"}. This record does not assert independent reproduction.

### IA2 only

Accuracy: 52.8. Result ID: 69bbb8cd47f34ce924a5a9d8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bac1e209131cea89ce3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bac1e209131cea89ce3.md>)

Recorded evaluation configuration: {"Model":"Qwen3-4B-Base","N":"4","Source Dataset":"FinS","OOD":"true"}. This record does not assert independent reproduction.

### SFT only

Accuracy: 49.9. Result ID: 69bbb8cd47f34ce924a5a9d7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bac1e209131cea89ce3.md>)

Recorded evaluation configuration: {"Model":"Qwen3-4B-Base","N":"4","Source Dataset":"FinS","OOD":"true"}. This record does not assert independent reproduction.

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