# Knowledge-Grounded Dialog on DoQA (Retrieval Metrics)

Source: [Knowledge-Grounded Dialog on DoQA (Retrieval Metrics)](<https://www.sota2.com/research/sota/knowledge-grounded-dialog-on-doqa-retrieval-metrics>)

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

Data updated: 2026-04-23T09:54:10.506Z

Evaluation of Knowledge-Grounded Dialog performance on the DoQA dataset, focusing on retrieval accuracy measured by Rank-based metrics (R@k and MRR).

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 | Knowledge-Grounded Dialog |
| Dataset (including any stated split) | DoQA |
| Metric | R@1 |
| 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

- [R@1](<https://www.sota2.com/research/sota/knowledge-grounded-dialog-on-doqa-retrieval-metrics.md?metric=R%401>): Higher is better; unit: PERCENT.

- [R@10](<https://www.sota2.com/research/sota/knowledge-grounded-dialog-on-doqa-retrieval-metrics.md?metric=R%4010>): Higher is better; unit: PERCENT.

- [MRR@10](<https://www.sota2.com/research/sota/knowledge-grounded-dialog-on-doqa-retrieval-metrics.md?metric=MRR%4010>): Higher is better; unit: PERCENT.

## Recorded results

| Method | R@1 | Result date | Report paper |
| --- | --- | --- | --- |
| JSA-RAG | 68.09 | Not recorded | 68fa7ae31e209131cea85b05 |
| VRAG | 68.01 | Not recorded | 68fa7ae31e209131cea85b05 |
| RAG | 67.61 | Not recorded | 68fa7ae31e209131cea85b05 |
| Base | 58.59 | Not recorded | 68fa7ae31e209131cea85b05 |

### JSA-RAG

R@1: 68.09. Result ID: 69e9ec3047f34ce924d18e93.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ae31e209131cea85b05.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ae31e209131cea85b05.md>)

Recorded evaluation configuration: {"Backbone":"BGE-large"}. This record does not assert independent reproduction.

### VRAG

R@1: 68.01. Result ID: 69e9ec3047f34ce924d18e92.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ae31e209131cea85b05.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d3a1e209131cea3892e.md>)

Recorded evaluation configuration: {"Backbone":"BGE-large"}. This record does not assert independent reproduction.

### RAG

R@1: 67.61. Result ID: 69e9ec3047f34ce924d18e91.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ae31e209131cea85b05.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: {"Backbone":"BGE-large"}. This record does not assert independent reproduction.

### Base

R@1: 58.59. Result ID: 69e9ec3047f34ce924d18e90.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ae31e209131cea85b05.md>)

Recorded evaluation configuration: {"Backbone":"BGE-large"}. This record does not assert independent reproduction.

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