# Direct Question Answering on PISTOL (A\_B)

Source: [Direct Question Answering on PISTOL (A\_B)](<https://www.sota2.com/research/sota/direct-question-answering-on-pistol-a_b>)

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

Data updated: 2026-05-28T06:51:19.014Z

Evaluation of Direct Question Answering performance on the PISTOL (A\_B) dataset, using metrics such as ROUGE-L and LLM-Judge.

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 | Direct Question Answering |
| Dataset (including any stated split) | PISTOL (A\_B) |
| Metric | ROUGE-L |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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

- [ROUGE-L](<https://www.sota2.com/research/sota/direct-question-answering-on-pistol-a_b.md?metric=ROUGE-L>): Higher is better; unit: PERCENT.

- [LLM Judge Score](<https://www.sota2.com/research/sota/direct-question-answering-on-pistol-a_b.md?metric=LLM%20Judge%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | ROUGE-L | Result date | Report paper |
| --- | --- | --- | --- |
| NPO | 79.1 | Not recorded | 68fa7c5d1e209131cea8dbff |
| NPO | 78.8 | Not recorded | 68fa7c5d1e209131cea8dbff |
| RMU | 76.5 | Not recorded | 68fa7c5d1e209131cea8dbff |
| RMU | 70.5 | Not recorded | 68fa7c5d1e209131cea8dbff |
| UNDIAL | 50.2 | Not recorded | 68fa7c5d1e209131cea8dbff |
| UNDIAL | 49.9 | Not recorded | 68fa7c5d1e209131cea8dbff |

### NPO

ROUGE-L: 79.1. Result ID: 6a17e435fbc373592c110b37.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c5d1e209131cea8dbff.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c5d1e209131cea8dbff.md>)

Recorded evaluation configuration: {"Variant":"Context-aware"}. This record does not assert independent reproduction.

### NPO

ROUGE-L: 78.8. Result ID: 6a17e435fbc373592c110b36.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c5d1e209131cea8dbff.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c5d1e209131cea8dbff.md>)

Recorded evaluation configuration: {"Variant":"Vanilla"}. This record does not assert independent reproduction.

### RMU

ROUGE-L: 76.5. Result ID: 6a17e435fbc373592c110b39.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c5d1e209131cea8dbff.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c5d1e209131cea8dbff.md>)

Recorded evaluation configuration: {"Variant":"Context-aware"}. This record does not assert independent reproduction.

### RMU

ROUGE-L: 70.5. Result ID: 6a17e435fbc373592c110b38.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c5d1e209131cea8dbff.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c5d1e209131cea8dbff.md>)

Recorded evaluation configuration: {"Variant":"Vanilla"}. This record does not assert independent reproduction.

### UNDIAL

ROUGE-L: 50.2. Result ID: 6a17e435fbc373592c110b3b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c5d1e209131cea8dbff.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c5d1e209131cea8dbff.md>)

Recorded evaluation configuration: {"Variant":"Context-aware"}. This record does not assert independent reproduction.

### UNDIAL

ROUGE-L: 49.9. Result ID: 6a17e435fbc373592c110b3a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c5d1e209131cea8dbff.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c5d1e209131cea8dbff.md>)

Recorded evaluation configuration: {"Variant":"Vanilla"}. This record does not assert independent reproduction.

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