# Conversation Disentanglement on Ubuntu (test)

Source: [Conversation Disentanglement on Ubuntu (test)](<https://www.sota2.com/research/sota/conversation-disentanglement-on-ubuntu-test>)

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

Data updated: 2026-02-26T06:08:01.724Z

Evaluation of Conversation Disentanglement performance on the test split of the Ubuntu dataset, using metrics including VI, 1-1, Precision, Recall, and F-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 | Conversation Disentanglement |
| Dataset (including any stated split) | Ubuntu (test) |
| Metric | VI |
| 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

- [VI](<https://www.sota2.com/research/sota/conversation-disentanglement-on-ubuntu-test.md?metric=VI>): Higher is better; unit: PERCENT.

- [1-1 Match Rate](<https://www.sota2.com/research/sota/conversation-disentanglement-on-ubuntu-test.md?metric=1-1%20Match%20Rate>): Higher is better; unit: PERCENT.

- [Precision](<https://www.sota2.com/research/sota/conversation-disentanglement-on-ubuntu-test.md?metric=Precision>): Higher is better; unit: PERCENT.

- [Recall](<https://www.sota2.com/research/sota/conversation-disentanglement-on-ubuntu-test.md?metric=Recall>): Higher is better; unit: PERCENT.

- [F-Score](<https://www.sota2.com/research/sota/conversation-disentanglement-on-ubuntu-test.md?metric=F-Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | VI | Result date | Report paper |
| --- | --- | --- | --- |
| x10 vote | 91.5 | Not recorded | 68fa67a71e209131cea177d9 |
| Feedforward | 91.3 | Not recorded | 68fa67a71e209131cea177d9 |
| Linear | 88.9 | Not recorded | 68fa67a71e209131cea177d9 |
| x10 union | 86.2 | Not recorded | 68fa67a71e209131cea177d9 |
| Elsner | 82.1 | Not recorded | 68fa67a71e209131cea177d9 |
| Lowe | 80.6 | Not recorded | 68fa67a71e209131cea177d9 |
| x10 intersect | 69.3 | Not recorded | 68fa67a71e209131cea177d9 |
| Previous | 66.1 | Not recorded | 68fa67a71e209131cea177d9 |

### x10 vote

VI: 91.5. Result ID: 698d3dc18b517eb4332009bb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa67a71e209131cea177d9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67a71e209131cea177d9.md>)

[Implementation](<https://jkk.name/irc-disentanglement>)

Recorded evaluation configuration: {"Ensemble Size":"10"}. This record does not assert independent reproduction.

### Feedforward

VI: 91.3. Result ID: 698d3dc18b517eb4332009b9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa67a71e209131cea177d9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67a71e209131cea177d9.md>)

[Implementation](<https://jkk.name/irc-disentanglement>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Linear

VI: 88.9. Result ID: 698d3dc18b517eb4332009b8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa67a71e209131cea177d9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67a71e209131cea177d9.md>)

[Implementation](<https://jkk.name/irc-disentanglement>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### x10 union

VI: 86.2. Result ID: 698d3dc18b517eb4332009ba.

[Reporting paper](<https://www.sota2.com/research/paper/68fa67a71e209131cea177d9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67a71e209131cea177d9.md>)

[Implementation](<https://jkk.name/irc-disentanglement>)

Recorded evaluation configuration: {"Ensemble Size":"10"}. This record does not assert independent reproduction.

### Elsner

VI: 82.1. Result ID: 698d3dc18b517eb4332009be.

[Reporting paper](<https://www.sota2.com/research/paper/68fa67a71e209131cea177d9.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Lowe

VI: 80.6. Result ID: 698d3dc18b517eb4332009bd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa67a71e209131cea177d9.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### x10 intersect

VI: 69.3. Result ID: 698d3dc18b517eb4332009bc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa67a71e209131cea177d9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67a71e209131cea177d9.md>)

[Implementation](<https://jkk.name/irc-disentanglement>)

Recorded evaluation configuration: {"Ensemble Size":"10"}. This record does not assert independent reproduction.

### Previous

VI: 66.1. Result ID: 698d3dc18b517eb4332009b7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa67a71e209131cea177d9.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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