# Sentence-level value detection on ValueEval English '24 (test)

Source: [Sentence-level value detection on ValueEval English '24 (test)](<https://www.sota2.com/research/sota/sentence-level-value-detection-on-valueeval-english-24-test>)

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

Data updated: 2026-02-26T05:51:27.501Z

Evaluation of models on detecting specific values within sentences using the ValueEval English '24 test set, typically measured by macro F1 score.

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 | Sentence-level value detection |
| Dataset (including any stated split) | ValueEval English '24 (test) |
| Metric | Macro F1 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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

- [Macro F1](<https://www.sota2.com/research/sota/sentence-level-value-detection-on-valueeval-english-24-test.md?metric=Macro%20F1>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Macro F1 | Result date | Report paper |
| --- | --- | --- | --- |
| DeBERTa Ensemble (Baseline + LIWC-22 + Prev-2) | 33.2 | Not recorded | 69705deae25ad2fa9d1ed7ec |
| DeBERTa + LIWC-22 | 32 | Not recorded | 69705deae25ad2fa9d1ed7ec |
| Gemma LLM Ensemble | 27.7 | Not recorded | 69705deae25ad2fa9d1ed7ec |
| Gemma-2-9B few-shot | 23.8 | Not recorded | 69705deae25ad2fa9d1ed7ec |

### DeBERTa Ensemble (Baseline + LIWC-22 + Prev-2)

Macro F1: 33.2. Result ID: 699677c85698665ec4bf48dc.

[Reporting paper](<https://www.sota2.com/research/paper/69705deae25ad2fa9d1ed7ec.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69705deae25ad2fa9d1ed7ec.md>)

Recorded evaluation configuration: {"Family":"Transformer (ensemble)","Architecture":"Direct ensemble","Voting":"soft vote","Threshold (t\*)":"0.29"}. This record does not assert independent reproduction.

### DeBERTa + LIWC-22

Macro F1: 32. Result ID: 699677c85698665ec4bf48db.

[Reporting paper](<https://www.sota2.com/research/paper/69705deae25ad2fa9d1ed7ec.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69705deae25ad2fa9d1ed7ec.md>)

Recorded evaluation configuration: {"Family":"Transformer (single)","Training":"tuned","Architecture":"Direct"}. This record does not assert independent reproduction.

### Gemma LLM Ensemble

Macro F1: 27.7. Result ID: 699677c85698665ec4bf48de.

[Reporting paper](<https://www.sota2.com/research/paper/69705deae25ad2fa9d1ed7ec.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69705deae25ad2fa9d1ed7ec.md>)

Recorded evaluation configuration: {"Family":"LLM (ensemble)","Architecture":"LLM ensemble","Components":"Gemma few-shot hier + Gemma QLoRA","Voting":"hard vote"}. This record does not assert independent reproduction.

### Gemma-2-9B few-shot

Macro F1: 23.8. Result ID: 699677c85698665ec4bf48dd.

[Reporting paper](<https://www.sota2.com/research/paper/69705deae25ad2fa9d1ed7ec.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69705deae25ad2fa9d1ed7ec.md>)

Recorded evaluation configuration: {"Family":"LLM (single)","Auxiliary":"SBERT presence gate","Architecture":"Hier. (presence gate)"}. This record does not assert independent reproduction.

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