# Dialogue State Tracking on ToDs benchmark GPT-2 backbone (test)

Source: [Dialogue State Tracking on ToDs benchmark GPT-2 backbone (test)](<https://www.sota2.com/research/sota/dialogue-state-tracking-on-tods-benchmark-gpt-2-backbone-test>)

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

Data updated: 2026-02-26T05:47:36.213Z

Evaluation of Dialogue State Tracking performance on the test split of the ToDs benchmark, specifically using a GPT-2 backbone configuration, measured using Joint Goal Accuracy (JGA).

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 State Tracking |
| Dataset (including any stated split) | ToDs benchmark GPT-2 backbone (test) |
| Metric | JGA |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 11 of 11 |
| 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

- [JGA](<https://www.sota2.com/research/sota/dialogue-state-tracking-on-tods-benchmark-gpt-2-backbone-test.md?metric=JGA>): Higher is better; unit: PERCENT.

## Recorded results

| Method | JGA | Result date | Report paper |
| --- | --- | --- | --- |
| MULTI | 50.03 | Not recorded | 68fa73471e209131cea5b810 |
| HESIT | 40.04 | Not recorded | 68fa73471e209131cea5b810 |
| UNIFORM | 39.92 | Not recorded | 68fa73471e209131cea5b810 |
| GSS | 39.8 | Not recorded | 68fa73471e209131cea5b810 |
| RANDOM | 39.54 | Not recorded | 68fa73471e209131cea5b810 |
| ARPER | 39.21 | Not recorded | 68fa73471e209131cea5b810 |
| VANILLA | 10.28 | Not recorded | 68fa73471e209131cea5b810 |
| EWC | 10.06 | Not recorded | 68fa73471e209131cea5b810 |
| L2 | 9.94 | Not recorded | 68fa73471e209131cea5b810 |
| A-GEM | 9.86 | Not recorded | 68fa73471e209131cea5b810 |
| LAMOL | 9.44 | Not recorded | 68fa73471e209131cea5b810 |

### MULTI

JGA: 50.03. Result ID: 6992cf1b3a6c31484911a672.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73471e209131cea5b810.md>)

Recorded evaluation configuration: {"Memory size (Mem)":"Full data","Evaluation type":"Modularized"}. This record does not assert independent reproduction.

### HESIT

JGA: 40.04. Result ID: 6992cf1b3a6c31484911a671.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73471e209131cea5b810.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73471e209131cea5b810.md>)

Recorded evaluation configuration: {"Memory size (Mem)":"t\|M\|","Evaluation type":"Modularized"}. This record does not assert independent reproduction.

### UNIFORM

JGA: 39.92. Result ID: 6992cf1b3a6c31484911a66e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73471e209131cea5b810.md>)

Recorded evaluation configuration: {"Memory size (Mem)":"t\|M\|","Evaluation type":"Modularized"}. This record does not assert independent reproduction.

### GSS

JGA: 39.8. Result ID: 6992cf1b3a6c31484911a66f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73471e209131cea5b810.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66981e209131cea1132f.md>)

Recorded evaluation configuration: {"Memory size (Mem)":"t\|M\|","Evaluation type":"Modularized"}. This record does not assert independent reproduction.

### RANDOM

JGA: 39.54. Result ID: 6992cf1b3a6c31484911a66d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73471e209131cea5b810.md>)

Recorded evaluation configuration: {"Memory size (Mem)":"t\|M\|","Evaluation type":"Modularized"}. This record does not assert independent reproduction.

### ARPER

JGA: 39.21. Result ID: 6992cf1b3a6c31484911a670.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73471e209131cea5b810.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa686f1e209131cea1c2b0.md>)

Recorded evaluation configuration: {"Memory size (Mem)":"t\|M\|","Evaluation type":"Modularized"}. This record does not assert independent reproduction.

### VANILLA

JGA: 10.28. Result ID: 6992cf1b3a6c31484911a668.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73471e209131cea5b810.md>)

Recorded evaluation configuration: {"Memory size (Mem)":"0","Evaluation type":"Modularized"}. This record does not assert independent reproduction.

### EWC

JGA: 10.06. Result ID: 6992cf1b3a6c31484911a66a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73471e209131cea5b810.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cb31e209131cea3555e.md>)

Recorded evaluation configuration: {"Memory size (Mem)":"0","Evaluation type":"Modularized"}. This record does not assert independent reproduction.

### L2

JGA: 9.94. Result ID: 6992cf1b3a6c31484911a669.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73471e209131cea5b810.md>)

Recorded evaluation configuration: {"Memory size (Mem)":"0","Evaluation type":"Modularized"}. This record does not assert independent reproduction.

### A-GEM

JGA: 9.86. Result ID: 6992cf1b3a6c31484911a66b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73471e209131cea5b810.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65371e209131cea090ac.md>)

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

Recorded evaluation configuration: {"Memory size (Mem)":"t\|M\|","Evaluation type":"Modularized"}. This record does not assert independent reproduction.

### LAMOL

JGA: 9.44. Result ID: 6992cf1b3a6c31484911a66c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73471e209131cea5b810.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66d51e209131cea12c0a.md>)

[Implementation](<https://github.com/jojotenya/LAMOL>)

Recorded evaluation configuration: {"Memory size (Mem)":"0","Evaluation type":"Modularized"}. This record does not assert independent reproduction.

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