# Open-domain dialogue on Wizard-of-Wikipedia KILT (test)

Source: [Open-domain dialogue on Wizard-of-Wikipedia KILT (test)](<https://www.sota2.com/research/sota/open-domain-dialogue-on-wizard-of-wikipedia-kilt-test>)

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

Data updated: 2026-02-26T05:43:11.445Z

Evaluation of Open-domain dialogue performance on the test split of the Wizard-of-Wikipedia KILT dataset variant, measured using F1, R-L, and U/s 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 | Open-domain dialogue |
| Dataset (including any stated split) | Wizard-of-Wikipedia KILT (test) |
| Metric | F1 Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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

- [F1 Score](<https://www.sota2.com/research/sota/open-domain-dialogue-on-wizard-of-wikipedia-kilt-test.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

- [R-L Score](<https://www.sota2.com/research/sota/open-domain-dialogue-on-wizard-of-wikipedia-kilt-test.md?metric=R-L%20Score>): Higher is better; unit: PERCENT.

- [Utterances per Second (U/s)](<https://www.sota2.com/research/sota/open-domain-dialogue-on-wizard-of-wikipedia-kilt-test.md?metric=Utterances%20per%20Second%20(U%2Fs)>): Higher is better; unit: SCALAR.

## Recorded results

| Method | F1 Score | Result date | Report paper |
| --- | --- | --- | --- |
| EMAT-FKSV | 15.78 | Not recorded | 68fa6dc31e209131cea3bead |
| EMAT-SKSV | 15.35 | Not recorded | 68fa6dc31e209131cea3bead |
| BART + DPR | 15.19 | Not recorded | 68fa6dc31e209131cea3bead |
| T5-base | 13.53 | Not recorded | 68fa6dc31e209131cea3bead |
| RAG | 13.11 | Not recorded | 68fa6dc31e209131cea3bead |
| BART-large | 12.86 | Not recorded | 68fa6dc31e209131cea3bead |
| Trans MemNet | 11.85 | Not recorded | 68fa6dc31e209131cea3bead |
| RePAQ w/ EMAT key encoder | 1.84 | Not recorded | 68fa6dc31e209131cea3bead |

### EMAT-FKSV

F1 Score: 15.78. Result ID: 698fdacb3a6c314849fc5956.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc31e209131cea3bead.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6dc31e209131cea3bead.md>)

[Implementation](<https://github.com/uclnlp/EMAT>)

Recorded evaluation configuration: {"Model architecture type":"Ours"}. This record does not assert independent reproduction.

### EMAT-SKSV

F1 Score: 15.35. Result ID: 698fdacb3a6c314849fc5957.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc31e209131cea3bead.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6dc31e209131cea3bead.md>)

[Implementation](<https://github.com/uclnlp/EMAT>)

Recorded evaluation configuration: {"Model architecture type":"Ours"}. This record does not assert independent reproduction.

### BART + DPR

F1 Score: 15.19. Result ID: 698fdacb3a6c314849fc5953.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc31e209131cea3bead.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a021e209131cea255d9.md>)

[Implementation](<https://github.com/facebookresearch/KILT>)

Recorded evaluation configuration: {"Model architecture type":"Retrieval-augmented models"}. This record does not assert independent reproduction.

### T5-base

F1 Score: 13.53. Result ID: 698fdacb3a6c314849fc5952.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc31e209131cea3bead.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa709e1e209131cea4c470.md>)

[Implementation](<https://github.com/google-research/text-to-text-transfer-transformer>)

Recorded evaluation configuration: {"Model architecture type":"Parametric models"}. This record does not assert independent reproduction.

### RAG

F1 Score: 13.11. Result ID: 698fdacb3a6c314849fc5954.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc31e209131cea3bead.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: {"Model architecture type":"Retrieval-augmented models"}. This record does not assert independent reproduction.

### BART-large

F1 Score: 12.86. Result ID: 698fdacb3a6c314849fc5951.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc31e209131cea3bead.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66921e209131cea10fff.md>)

Recorded evaluation configuration: {"Model architecture type":"Parametric models"}. This record does not assert independent reproduction.

### Trans MemNet

F1 Score: 11.85. Result ID: 698fdacb3a6c314849fc5950.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc31e209131cea3bead.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65651e209131cea09f24.md>)

Recorded evaluation configuration: {"Model architecture type":"Parametric models"}. This record does not assert independent reproduction.

### RePAQ w/ EMAT key encoder

F1 Score: 1.84. Result ID: 698fdacb3a6c314849fc5955.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dc31e209131cea3bead.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69521e209131cea2189a.md>)

Recorded evaluation configuration: {"Model architecture type":"Retrieval-only models"}. This record does not assert independent reproduction.

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