# Deriving driving requirements on Tagged scenarios Mandatory behaviors (test)

Source: [Deriving driving requirements on Tagged scenarios Mandatory behaviors (test)](<https://www.sota2.com/research/sota/deriving-driving-requirements-on-tagged-scenarios-mandatory-behaviors-test>)

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

Data updated: 2026-04-28T10:31:28.928Z

Evaluation of the system's ability to derive driving requirements from the 'Tagged scenarios Mandatory behaviors' test set, assessed using NLP metrics like 1-gram F1 and BERTScore F1.

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 | Deriving driving requirements |
| Dataset (including any stated split) | Tagged scenarios Mandatory behaviors (test) |
| Metric | 1-gram F1 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 7 of 7 |
| 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

- [1-gram F1](<https://www.sota2.com/research/sota/deriving-driving-requirements-on-tagged-scenarios-mandatory-behaviors-test.md?metric=1-gram%20F1>): Higher is better; unit: PERCENT.

- [2-gram F1](<https://www.sota2.com/research/sota/deriving-driving-requirements-on-tagged-scenarios-mandatory-behaviors-test.md?metric=2-gram%20F1>): Higher is better; unit: PERCENT.

- [BERTScore F1](<https://www.sota2.com/research/sota/deriving-driving-requirements-on-tagged-scenarios-mandatory-behaviors-test.md?metric=BERTScore%20F1>): Higher is better; unit: PERCENT.

## Recorded results

| Method | 1-gram F1 | Result date | Report paper |
| --- | --- | --- | --- |
| TGA | 73.3 | Not recorded | 69f03f8155a3c32af89fa5e3 |
| VanillaRAG | 36.4 | Not recorded | 69f03f8155a3c32af89fa5e3 |
| GraphRAG | 31.4 | Not recorded | 69f03f8155a3c32af89fa5e3 |
| Lora | 26.5 | Not recorded | 69f03f8155a3c32af89fa5e3 |
| Zero-shot+thinking | 26.1 | Not recorded | 69f03f8155a3c32af89fa5e3 |
| Zero-shot | 23.4 | Not recorded | 69f03f8155a3c32af89fa5e3 |
| Zero-shot+knowledge | 21.9 | Not recorded | 69f03f8155a3c32af89fa5e3 |

### TGA

1-gram F1: 73.3. Result ID: 69f08c4d47f34ce924d73333.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f8155a3c32af89fa5e3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69f03f8155a3c32af89fa5e3.md>)

Recorded evaluation configuration: {"Category":"RAG"}. This record does not assert independent reproduction.

### VanillaRAG

1-gram F1: 36.4. Result ID: 69f08c4d47f34ce924d73331.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f8155a3c32af89fa5e3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69b91e209131cea23c26.md>)

[Implementation](<https://github.com/huggingface/transformers/blob/master/examples/rag/>)

Recorded evaluation configuration: {"Category":"RAG"}. This record does not assert independent reproduction.

### GraphRAG

1-gram F1: 31.4. Result ID: 69f08c4d47f34ce924d73332.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f8155a3c32af89fa5e3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa770d1e209131cea70c5a.md>)

Recorded evaluation configuration: {"Category":"RAG"}. This record does not assert independent reproduction.

### Lora

1-gram F1: 26.5. Result ID: 69f08c4d47f34ce924d73330.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f8155a3c32af89fa5e3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b121e209131cea2bf59.md>)

[Implementation](<https://github.com/microsoft/LoRA>)

Recorded evaluation configuration: {"Category":"Fine-tuning"}. This record does not assert independent reproduction.

### Zero-shot+thinking

1-gram F1: 26.1. Result ID: 69f08c4d47f34ce924d7332e.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f8155a3c32af89fa5e3.md>)

Recorded evaluation configuration: {"Category":"Inference-only"}. This record does not assert independent reproduction.

### Zero-shot

1-gram F1: 23.4. Result ID: 69f08c4d47f34ce924d7332d.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f8155a3c32af89fa5e3.md>)

Recorded evaluation configuration: {"Category":"Inference-only"}. This record does not assert independent reproduction.

### Zero-shot+knowledge

1-gram F1: 21.9. Result ID: 69f08c4d47f34ce924d7332f.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f8155a3c32af89fa5e3.md>)

Recorded evaluation configuration: {"Category":"Inference-only"}. This record does not assert independent reproduction.

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