# Dialogue Response Selection on DailyDialog reformatted multiple-choice (test)

Source: [Dialogue Response Selection on DailyDialog reformatted multiple-choice (test)](<https://www.sota2.com/research/sota/dialogue-response-selection-on-dailydialog-reformatted-multiple-choice-test>)

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

Data updated: 2026-02-26T05:29:41.478Z

Evaluation of dialogue response selection performance on the test split of the reformatted multiple-choice version of the DailyDialog dataset, measured using accuracy.

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 Response Selection |
| Dataset (including any stated split) | DailyDialog reformatted multiple-choice (test) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 16 of 16 |
| 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

- [Accuracy](<https://www.sota2.com/research/sota/dialogue-response-selection-on-dailydialog-reformatted-multiple-choice-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Delta](<https://www.sota2.com/research/sota/dialogue-response-selection-on-dailydialog-reformatted-multiple-choice-test.md?metric=Delta>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| SirLLM | 90.35 | Not recorded | 68fa733f1e209131cea5b3c3 |
| StreamLLM | 85.35 | Not recorded | 68fa733f1e209131cea5b3c3 |
| SirLLM | 83.85 | Not recorded | 68fa733f1e209131cea5b3c3 |
| RandomLLM | 82.17 | Not recorded | 68fa733f1e209131cea5b3c3 |
| StreamLLM | 76.9 | Not recorded | 68fa733f1e209131cea5b3c3 |
| SirLLM | 71.4 | Not recorded | 68fa733f1e209131cea5b3c3 |
| RandomLLM | 71.1 | Not recorded | 68fa733f1e209131cea5b3c3 |
| StreamLLM | 71.1 | Not recorded | 68fa733f1e209131cea5b3c3 |
| IntervalLLM | 70.7 | Not recorded | 68fa733f1e209131cea5b3c3 |
| RandomLLM | 69.27 | Not recorded | 68fa733f1e209131cea5b3c3 |
| IntervalLLM | 65.2 | Not recorded | 68fa733f1e209131cea5b3c3 |
| IntervalLLM | 62.05 | Not recorded | 68fa733f1e209131cea5b3c3 |
| SirLLM | 59.15 | Not recorded | 68fa733f1e209131cea5b3c3 |
| StreamLLM | 57.55 | Not recorded | 68fa733f1e209131cea5b3c3 |
| RandomLLM | 57.48 | Not recorded | 68fa733f1e209131cea5b3c3 |
| IntervalLLM | 54.45 | Not recorded | 68fa733f1e209131cea5b3c3 |

### SirLLM

Accuracy: 90.35. Result ID: 6992cc603a6c314849119251.

[Reporting paper](<https://www.sota2.com/research/paper/68fa733f1e209131cea5b3c3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa733f1e209131cea5b3c3.md>)

[Implementation](<https://github.com/Zoeyyao27/SirLLM>)

Recorded evaluation configuration: {"Backbone":"Yi-34b","Attention Sink Size":4,"# Entropy":508,"# Recent":0,"ηdecay":0.7}. This record does not assert independent reproduction.

### StreamLLM

Accuracy: 85.35. Result ID: 6992cc603a6c31484911924e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa733f1e209131cea5b3c3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72d71e209131cea58d79.md>)

Recorded evaluation configuration: {"Backbone":"Yi-34b","Attention Sink Size":4,"# Entropy":0,"# Recent":508,"ηdecay":1}. This record does not assert independent reproduction.

### SirLLM

Accuracy: 83.85. Result ID: 6992cc603a6c31484911924d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa733f1e209131cea5b3c3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa733f1e209131cea5b3c3.md>)

[Implementation](<https://github.com/Zoeyyao27/SirLLM>)

Recorded evaluation configuration: {"Backbone":"Yi-6b","Attention Sink Size":4,"# Entropy":508,"# Recent":0,"ηdecay":0.7}. This record does not assert independent reproduction.

### RandomLLM

Accuracy: 82.17. Result ID: 6992cc603a6c31484911924f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa733f1e209131cea5b3c3.md>)

Recorded evaluation configuration: {"Backbone":"Yi-34b","Attention Sink Size":4,"# Entropy":508,"# Recent":0,"ηdecay":1}. This record does not assert independent reproduction.

### StreamLLM

Accuracy: 76.9. Result ID: 6992cc603a6c31484911924a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa733f1e209131cea5b3c3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72d71e209131cea58d79.md>)

Recorded evaluation configuration: {"Backbone":"Yi-6b","Attention Sink Size":4,"# Entropy":0,"# Recent":508,"ηdecay":1}. This record does not assert independent reproduction.

### SirLLM

Accuracy: 71.4. Result ID: 6992cc603a6c314849119259.

[Reporting paper](<https://www.sota2.com/research/paper/68fa733f1e209131cea5b3c3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa733f1e209131cea5b3c3.md>)

[Implementation](<https://github.com/Zoeyyao27/SirLLM>)

Recorded evaluation configuration: {"Backbone":"Vicuna-13b","Attention Sink Size":4,"# Entropy":508,"# Recent":0,"ηdecay":0.6}. This record does not assert independent reproduction.

### RandomLLM

Accuracy: 71.1. Result ID: 6992cc603a6c31484911924b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa733f1e209131cea5b3c3.md>)

Recorded evaluation configuration: {"Backbone":"Yi-6b","Attention Sink Size":4,"# Entropy":508,"# Recent":0,"ηdecay":1}. This record does not assert independent reproduction.

### StreamLLM

Accuracy: 71.1. Result ID: 6992cc603a6c314849119256.

[Reporting paper](<https://www.sota2.com/research/paper/68fa733f1e209131cea5b3c3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72d71e209131cea58d79.md>)

Recorded evaluation configuration: {"Backbone":"Vicuna-13b","Attention Sink Size":4,"# Entropy":0,"# Recent":508,"ηdecay":1}. This record does not assert independent reproduction.

### IntervalLLM

Accuracy: 70.7. Result ID: 6992cc603a6c314849119250.

[Reporting paper](<https://www.sota2.com/research/paper/68fa733f1e209131cea5b3c3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65aa1e209131cea0bc26.md>)

Recorded evaluation configuration: {"Backbone":"Yi-34b","Attention Sink Size":4,"# Entropy":508,"# Recent":0,"ηdecay":1}. This record does not assert independent reproduction.

### RandomLLM

Accuracy: 69.27. Result ID: 6992cc603a6c314849119257.

[Reporting paper](<https://www.sota2.com/research/paper/68fa733f1e209131cea5b3c3.md>)

Recorded evaluation configuration: {"Backbone":"Vicuna-13b","Attention Sink Size":4,"# Entropy":508,"# Recent":0,"ηdecay":1}. This record does not assert independent reproduction.

### IntervalLLM

Accuracy: 65.2. Result ID: 6992cc603a6c31484911924c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa733f1e209131cea5b3c3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65aa1e209131cea0bc26.md>)

Recorded evaluation configuration: {"Backbone":"Yi-6b","Attention Sink Size":4,"# Entropy":508,"# Recent":0,"ηdecay":1}. This record does not assert independent reproduction.

### IntervalLLM

Accuracy: 62.05. Result ID: 6992cc603a6c314849119258.

[Reporting paper](<https://www.sota2.com/research/paper/68fa733f1e209131cea5b3c3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65aa1e209131cea0bc26.md>)

Recorded evaluation configuration: {"Backbone":"Vicuna-13b","Attention Sink Size":4,"# Entropy":508,"# Recent":0,"ηdecay":1}. This record does not assert independent reproduction.

### SirLLM

Accuracy: 59.15. Result ID: 6992cc603a6c314849119255.

[Reporting paper](<https://www.sota2.com/research/paper/68fa733f1e209131cea5b3c3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa733f1e209131cea5b3c3.md>)

[Implementation](<https://github.com/Zoeyyao27/SirLLM>)

Recorded evaluation configuration: {"Backbone":"Vicuna-7b","Attention Sink Size":4,"# Entropy":508,"# Recent":0,"ηdecay":0.5}. This record does not assert independent reproduction.

### StreamLLM

Accuracy: 57.55. Result ID: 6992cc603a6c314849119252.

[Reporting paper](<https://www.sota2.com/research/paper/68fa733f1e209131cea5b3c3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72d71e209131cea58d79.md>)

Recorded evaluation configuration: {"Backbone":"Vicuna-7b","Attention Sink Size":4,"# Entropy":0,"# Recent":508,"ηdecay":1}. This record does not assert independent reproduction.

### RandomLLM

Accuracy: 57.48. Result ID: 6992cc603a6c314849119253.

[Reporting paper](<https://www.sota2.com/research/paper/68fa733f1e209131cea5b3c3.md>)

Recorded evaluation configuration: {"Backbone":"Vicuna-7b","Attention Sink Size":4,"# Entropy":508,"# Recent":0,"ηdecay":1}. This record does not assert independent reproduction.

### IntervalLLM

Accuracy: 54.45. Result ID: 6992cc603a6c314849119254.

[Reporting paper](<https://www.sota2.com/research/paper/68fa733f1e209131cea5b3c3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65aa1e209131cea0bc26.md>)

Recorded evaluation configuration: {"Backbone":"Vicuna-7b","Attention Sink Size":4,"# Entropy":508,"# Recent":0,"ηdecay":1}. This record does not assert independent reproduction.

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