# Question Answering Feedback Generation on QA-FEEDBACK (test)

Source: [Question Answering Feedback Generation on QA-FEEDBACK (test)](<https://www.sota2.com/research/sota/question-answering-feedback-generation-on-qa-feedback-test>)

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

Data updated: 2026-02-26T06:02:30.597Z

Evaluation of model performance on the test split of the QA-FEEDBACK dataset for the Question Answering Feedback Generation task, measured using Rs1, Rs2, Rs3, and Rouge metrics.

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 | Question Answering Feedback Generation |
| Dataset (including any stated split) | QA-FEEDBACK (test) |
| Metric | Rs1 (Relevance) |
| Unit | SCALAR |
| 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

- [Rs1 (Relevance)](<https://www.sota2.com/research/sota/question-answering-feedback-generation-on-qa-feedback-test.md?metric=Rs1%20(Relevance)>): Higher is better; unit: SCALAR.

- [Rs2 (Factuality)](<https://www.sota2.com/research/sota/question-answering-feedback-generation-on-qa-feedback-test.md?metric=Rs2%20(Factuality)>): Higher is better; unit: SCALAR.

- [Rs3 (Completeness)](<https://www.sota2.com/research/sota/question-answering-feedback-generation-on-qa-feedback-test.md?metric=Rs3%20(Completeness)>): Higher is better; unit: SCALAR.

- [ROUGE Score](<https://www.sota2.com/research/sota/question-answering-feedback-generation-on-qa-feedback-test.md?metric=ROUGE%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Rs1 (Relevance) | Result date | Report paper |
| --- | --- | --- | --- |
| SFT | 0.513 | Not recorded | 68fa71021e209131cea4e83c |
| FINE-GRAINED RLHF | 0.513 | Not recorded | 68fa71021e209131cea4e83c |
| SFT-Full | 0.508 | Not recorded | 68fa71021e209131cea4e83c |
| Pref. RLHF | 0.482 | Not recorded | 68fa71021e209131cea4e83c |

### SFT

Rs1 (Relevance): 0.513. Result ID: 699187f03a6c31484908c434.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71021e209131cea4e83c.md>)

Recorded evaluation configuration: {"training":"Supervised Fine-Tuning"}. This record does not assert independent reproduction.

### FINE-GRAINED RLHF

Rs1 (Relevance): 0.513. Result ID: 699187f03a6c31484908c436.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71021e209131cea4e83c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71021e209131cea4e83c.md>)

[Implementation](<https://finegrainedrlhf.github.io/>)

Recorded evaluation configuration: {"base\_model":"SFT","training":"Fine-Grained RLHF"}. This record does not assert independent reproduction.

### SFT-Full

Rs1 (Relevance): 0.508. Result ID: 699187f03a6c31484908c433.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71021e209131cea4e83c.md>)

Recorded evaluation configuration: {"training":"Supervised Fine-Tuning Full"}. This record does not assert independent reproduction.

### Pref. RLHF

Rs1 (Relevance): 0.482. Result ID: 699187f03a6c31484908c435.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71021e209131cea4e83c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bf71e209131cea314c0.md>)

[Implementation](<https://github.com/openai/following-instructions-human-feedback>)

Recorded evaluation configuration: {"base\_model":"SFT","training":"Preference RLHF"}. This record does not assert independent reproduction.

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