# Dialogue Generation on 4 dialogue datasets Aggregate (test val)

Source: [Dialogue Generation on 4 dialogue datasets Aggregate (test val)](<https://www.sota2.com/research/sota/dialogue-generation-on-4-dialogue-datasets-aggregate-test-val>)

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

Data updated: 2026-02-26T05:40:49.838Z

Evaluation of Dialogue Generation performance across an aggregate test/validation set comprising four distinct dialogue datasets, measured using Dialogue Average F1 score.

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 | Dialogue Generation |
| Dataset (including any stated split) | 4 dialogue datasets Aggregate (test val) |
| Metric | Dialogue Avg F1 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 15 of 15 |
| 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

- [Dialogue Avg F1](<https://www.sota2.com/research/sota/dialogue-generation-on-4-dialogue-datasets-aggregate-test-val.md?metric=Dialogue%20Avg%20F1>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Dialogue Avg F1 | Result date | Report paper |
| --- | --- | --- | --- |
| OPT | 12.9 | Not recorded | 68fa6e421e209131cea3ec45 |
| NEO + UL | 12.5 | Not recorded | 68fa6e421e209131cea3ec45 |
| OPT | 12.4 | Not recorded | 68fa6e421e209131cea3ec45 |
| NEO + UL | 11.6 | Not recorded | 68fa6e421e209131cea3ec45 |
| NEO | 11.5 | Not recorded | 68fa6e421e209131cea3ec45 |
| NEO | 11.5 | Not recorded | 68fa6e421e209131cea3ec45 |
| NEO + UL+ | 11.1 | Not recorded | 68fa6e421e209131cea3ec45 |
| OPT | 10.2 | Not recorded | 68fa6e421e209131cea3ec45 |
| NEO | 9.4 | Not recorded | 68fa6e421e209131cea3ec45 |
| NEO + UL+ | 8.5 | Not recorded | 68fa6e421e209131cea3ec45 |
| NEO + UL | 8 | Not recorded | 68fa6e421e209131cea3ec45 |
| NEO + DPD+ | 7.3 | Not recorded | 68fa6e421e209131cea3ec45 |
| NEO + DPD+ | 7.1 | Not recorded | 68fa6e421e209131cea3ec45 |
| NEO + DPD+ | 6.9 | Not recorded | 68fa6e421e209131cea3ec45 |
| NEO + UL+ | 2.6 | Not recorded | 68fa6e421e209131cea3ec45 |

### OPT

Dialogue Avg F1: 12.9. Result ID: 699020e03a6c314849fe4e48.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e421e209131cea3ec45.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cda1e209131cea36474.md>)

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

Recorded evaluation configuration: {"Params":"2.7B","Epoch":null}. This record does not assert independent reproduction.

### NEO + UL

Dialogue Avg F1: 12.5. Result ID: 699020e03a6c314849fe4e4b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e421e209131cea3ec45.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e421e209131cea3ec45.md>)

[Implementation](<https://github.com/joeljang/knowledge-unlearning>)

Recorded evaluation configuration: {"Params":"2.7B","Epoch":5.4}. This record does not assert independent reproduction.

### OPT

Dialogue Avg F1: 12.4. Result ID: 699020e03a6c314849fe4e43.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e421e209131cea3ec45.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cda1e209131cea36474.md>)

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

Recorded evaluation configuration: {"Params":"1.3B","Epoch":null}. This record does not assert independent reproduction.

### NEO + UL

Dialogue Avg F1: 11.6. Result ID: 699020e03a6c314849fe4e46.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e421e209131cea3ec45.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e421e209131cea3ec45.md>)

[Implementation](<https://github.com/joeljang/knowledge-unlearning>)

Recorded evaluation configuration: {"Params":"1.3B","Epoch":8}. This record does not assert independent reproduction.

### NEO

Dialogue Avg F1: 11.5. Result ID: 699020e03a6c314849fe4e44.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e421e209131cea3ec45.md>)

Recorded evaluation configuration: {"Params":"1.3B","Epoch":null}. This record does not assert independent reproduction.

### NEO

Dialogue Avg F1: 11.5. Result ID: 699020e03a6c314849fe4e49.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e421e209131cea3ec45.md>)

Recorded evaluation configuration: {"Params":"2.7B","Epoch":null}. This record does not assert independent reproduction.

### NEO + UL+

Dialogue Avg F1: 11.1. Result ID: 699020e03a6c314849fe4e4c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e421e209131cea3ec45.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e421e209131cea3ec45.md>)

[Implementation](<https://github.com/joeljang/knowledge-unlearning>)

Recorded evaluation configuration: {"Params":"2.7B","Epoch":10.8}. This record does not assert independent reproduction.

### OPT

Dialogue Avg F1: 10.2. Result ID: 699020e03a6c314849fe4e3e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e421e209131cea3ec45.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cda1e209131cea36474.md>)

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

Recorded evaluation configuration: {"Params":"125M","Epoch":null}. This record does not assert independent reproduction.

### NEO

Dialogue Avg F1: 9.4. Result ID: 699020e03a6c314849fe4e3f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e421e209131cea3ec45.md>)

Recorded evaluation configuration: {"Params":"125M","Epoch":null}. This record does not assert independent reproduction.

### NEO + UL+

Dialogue Avg F1: 8.5. Result ID: 699020e03a6c314849fe4e47.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e421e209131cea3ec45.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e421e209131cea3ec45.md>)

[Implementation](<https://github.com/joeljang/knowledge-unlearning>)

Recorded evaluation configuration: {"Params":"1.3B","Epoch":13.8}. This record does not assert independent reproduction.

### NEO + UL

Dialogue Avg F1: 8. Result ID: 699020e03a6c314849fe4e41.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e421e209131cea3ec45.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e421e209131cea3ec45.md>)

[Implementation](<https://github.com/joeljang/knowledge-unlearning>)

Recorded evaluation configuration: {"Params":"125M","Epoch":11}. This record does not assert independent reproduction.

### NEO + DPD+

Dialogue Avg F1: 7.3. Result ID: 699020e03a6c314849fe4e40.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e421e209131cea3ec45.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e421e209131cea3ec45.md>)

[Implementation](<https://github.com/joeljang/knowledge-unlearning>)

Recorded evaluation configuration: {"Params":"125M","Epoch":null}. This record does not assert independent reproduction.

### NEO + DPD+

Dialogue Avg F1: 7.1. Result ID: 699020e03a6c314849fe4e45.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e421e209131cea3ec45.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e421e209131cea3ec45.md>)

[Implementation](<https://github.com/joeljang/knowledge-unlearning>)

Recorded evaluation configuration: {"Params":"1.3B","Epoch":null}. This record does not assert independent reproduction.

### NEO + DPD+

Dialogue Avg F1: 6.9. Result ID: 699020e03a6c314849fe4e4a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e421e209131cea3ec45.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e421e209131cea3ec45.md>)

[Implementation](<https://github.com/joeljang/knowledge-unlearning>)

Recorded evaluation configuration: {"Params":"2.7B","Epoch":null}. This record does not assert independent reproduction.

### NEO + UL+

Dialogue Avg F1: 2.6. Result ID: 699020e03a6c314849fe4e42.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e421e209131cea3ec45.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e421e209131cea3ec45.md>)

[Implementation](<https://github.com/joeljang/knowledge-unlearning>)

Recorded evaluation configuration: {"Params":"125M","Epoch":17.2}. This record does not assert independent reproduction.

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