# End-task Classification on Continual DAP Domain Suite Restaurant, ACL, AI, Phone, Camera, PubMed

Source: [End-task Classification on Continual DAP Domain Suite Restaurant, ACL, AI, Phone, Camera, PubMed](<https://www.sota2.com/research/sota/end-task-classification-on-continual-dap-domain-suite-restaurant-acl-ai-phone-camera-pubmed>)

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

Data updated: 2026-02-26T06:02:09.311Z

Evaluation of End-task Classification performance across a suite of six domains: Restaurant, ACL, AI, Phone, Camera, and PubMed, reporting per-domain accuracy/F1 and overall averages, including forgetting 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 | End-task Classification |
| Dataset (including any stated split) | Continual DAP Domain Suite Restaurant, ACL, AI, Phone, Camera, PubMed |
| Metric | Restaurant Macro F1 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 17 of 17 |
| 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

- [Restaurant Macro F1](<https://www.sota2.com/research/sota/end-task-classification-on-continual-dap-domain-suite-restaurant-acl-ai-phone-camera-pubmed.md?metric=Restaurant%20Macro%20F1>): Higher is better; unit: PERCENT.

- [Restaurant Accuracy](<https://www.sota2.com/research/sota/end-task-classification-on-continual-dap-domain-suite-restaurant-acl-ai-phone-camera-pubmed.md?metric=Restaurant%20Accuracy>): Higher is better; unit: PERCENT.

- [ACL Accuracy](<https://www.sota2.com/research/sota/end-task-classification-on-continual-dap-domain-suite-restaurant-acl-ai-phone-camera-pubmed.md?metric=ACL%20Accuracy>): Higher is better; unit: PERCENT.

- [ACL Macro F1](<https://www.sota2.com/research/sota/end-task-classification-on-continual-dap-domain-suite-restaurant-acl-ai-phone-camera-pubmed.md?metric=ACL%20Macro%20F1>): Higher is better; unit: PERCENT.

- [AI Accuracy](<https://www.sota2.com/research/sota/end-task-classification-on-continual-dap-domain-suite-restaurant-acl-ai-phone-camera-pubmed.md?metric=AI%20Accuracy>): Higher is better; unit: PERCENT.

- [AI Macro F1](<https://www.sota2.com/research/sota/end-task-classification-on-continual-dap-domain-suite-restaurant-acl-ai-phone-camera-pubmed.md?metric=AI%20Macro%20F1>): Higher is better; unit: PERCENT.

- [Phone Accuracy](<https://www.sota2.com/research/sota/end-task-classification-on-continual-dap-domain-suite-restaurant-acl-ai-phone-camera-pubmed.md?metric=Phone%20Accuracy>): Higher is better; unit: PERCENT.

- [Phone Macro F1](<https://www.sota2.com/research/sota/end-task-classification-on-continual-dap-domain-suite-restaurant-acl-ai-phone-camera-pubmed.md?metric=Phone%20Macro%20F1>): Higher is better; unit: PERCENT.

- [Camera Accuracy](<https://www.sota2.com/research/sota/end-task-classification-on-continual-dap-domain-suite-restaurant-acl-ai-phone-camera-pubmed.md?metric=Camera%20Accuracy>): Higher is better; unit: PERCENT.

- [Camera Macro F1](<https://www.sota2.com/research/sota/end-task-classification-on-continual-dap-domain-suite-restaurant-acl-ai-phone-camera-pubmed.md?metric=Camera%20Macro%20F1>): Higher is better; unit: PERCENT.

- [PubMed Accuracy](<https://www.sota2.com/research/sota/end-task-classification-on-continual-dap-domain-suite-restaurant-acl-ai-phone-camera-pubmed.md?metric=PubMed%20Accuracy>): Higher is better; unit: PERCENT.

- [PubMed Micro F1](<https://www.sota2.com/research/sota/end-task-classification-on-continual-dap-domain-suite-restaurant-acl-ai-phone-camera-pubmed.md?metric=PubMed%20Micro%20F1>): Higher is better; unit: PERCENT.

- [Average Accuracy](<https://www.sota2.com/research/sota/end-task-classification-on-continual-dap-domain-suite-restaurant-acl-ai-phone-camera-pubmed.md?metric=Average%20Accuracy>): Higher is better; unit: PERCENT.

- [Average Macro F1](<https://www.sota2.com/research/sota/end-task-classification-on-continual-dap-domain-suite-restaurant-acl-ai-phone-camera-pubmed.md?metric=Average%20Macro%20F1>): Higher is better; unit: PERCENT.

- [Restaurant Forgetting Macro F1](<https://www.sota2.com/research/sota/end-task-classification-on-continual-dap-domain-suite-restaurant-acl-ai-phone-camera-pubmed.md?metric=Restaurant%20Forgetting%20Macro%20F1>): Lower is better; unit: PERCENT.

- [Restaurant Forgetting Accuracy](<https://www.sota2.com/research/sota/end-task-classification-on-continual-dap-domain-suite-restaurant-acl-ai-phone-camera-pubmed.md?metric=Restaurant%20Forgetting%20Accuracy>): Lower is better; unit: PERCENT.

## Recorded results

| Method | Restaurant Macro F1 | Result date | Report paper |
| --- | --- | --- | --- |
| Pool | 0.8096 | Not recorded | 68fa6f041e209131cea43478 |
| DAP-RoBERTa | 0.8084 | Not recorded | 68fa6f041e209131cea43478 |
| DAS | 0.8034 | Not recorded | 68fa6f041e209131cea43478 |
| DAP-Adapter | 0.8019 | Not recorded | 68fa6f041e209131cea43478 |
| NCL-Adapter | 0.8013 | Not recorded | 68fa6f041e209131cea43478 |
| DEMIX | 0.7999 | Not recorded | 68fa6f041e209131cea43478 |
| CLASSIC | 0.7989 | Not recorded | 68fa6f041e209131cea43478 |
| RoBERTa | 0.7981 | Not recorded | 68fa6f041e209131cea43478 |
| NCL | 0.7952 | Not recorded | 68fa6f041e209131cea43478 |
| HAT-Adapter | 0.7929 | Not recorded | 68fa6f041e209131cea43478 |
| DAP-Prompt | 0.79 | Not recorded | 68fa6f041e209131cea43478 |
| BCL | 0.7897 | Not recorded | 68fa6f041e209131cea43478 |
| KD | 0.7805 | Not recorded | 68fa6f041e209131cea43478 |
| HAT | 0.7642 | Not recorded | 68fa6f041e209131cea43478 |
| HAT-All | 0.7494 | Not recorded | 68fa6f041e209131cea43478 |
| EWC | 0.7117 | Not recorded | 68fa6f041e209131cea43478 |
| DER++ | 0.6396 | Not recorded | 68fa6f041e209131cea43478 |

### Pool

Restaurant Macro F1: 0.8096. Result ID: 69908e843a6c314849017051.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f041e209131cea43478.md>)

Recorded evaluation configuration: {"Category":"Non-CL","Model":"Pool"}. This record does not assert independent reproduction.

### DAP-RoBERTa

Restaurant Macro F1: 0.8084. Result ID: 69908e843a6c314849017053.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f041e209131cea43478.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa677a1e209131cea16a90.md>)

Recorded evaluation configuration: {"Category":"Non-CL","Model":"DAP-RoBERTa"}. This record does not assert independent reproduction.

### DAS

Restaurant Macro F1: 0.8034. Result ID: 69908e843a6c314849017061.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f041e209131cea43478.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f041e209131cea43478.md>)

[Implementation](<https://github.com/UIC-Liu-Lab/ContinualLM>)

Recorded evaluation configuration: {"Category":"CL DAP-train","Model":"DAS"}. This record does not assert independent reproduction.

### DAP-Adapter

Restaurant Macro F1: 0.8019. Result ID: 69908e843a6c314849017054.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f041e209131cea43478.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65e31e209131cea0d324.md>)

[Implementation](<https://github.com/google-research/adapter-bert>)

Recorded evaluation configuration: {"Category":"Non-CL","Model":"DAP-Adapter"}. This record does not assert independent reproduction.

### NCL-Adapter

Restaurant Macro F1: 0.8013. Result ID: 69908e843a6c314849017057.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f041e209131cea43478.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65e31e209131cea0d324.md>)

[Implementation](<https://github.com/google-research/adapter-bert>)

Recorded evaluation configuration: {"Category":"CL DAP-train","Model":"NCL-Adapter"}. This record does not assert independent reproduction.

### DEMIX

Restaurant Macro F1: 0.7999. Result ID: 69908e843a6c314849017058.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f041e209131cea43478.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a981e209131cea29372.md>)

Recorded evaluation configuration: {"Category":"CL DAP-train","Model":"DEMIX"}. This record does not assert independent reproduction.

### CLASSIC

Restaurant Macro F1: 0.7989. Result ID: 69908e843a6c31484901705a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f041e209131cea43478.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b7f1e209131cea2e980.md>)

Recorded evaluation configuration: {"Category":"CL DAP-train","Model":"CLASSIC"}. This record does not assert independent reproduction.

### RoBERTa

Restaurant Macro F1: 0.7981. Result ID: 69908e843a6c314849017052.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f041e209131cea43478.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66131e209131cea0e18b.md>)

[Implementation](<https://github.com/pytorch/fairseq>)

Recorded evaluation configuration: {"Category":"Non-CL","Model":"RoBERTa"}. This record does not assert independent reproduction.

### NCL

Restaurant Macro F1: 0.7952. Result ID: 69908e843a6c314849017056.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f041e209131cea43478.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa677a1e209131cea16a90.md>)

Recorded evaluation configuration: {"Category":"CL DAP-train","Model":"NCL"}. This record does not assert independent reproduction.

### HAT-Adapter

Restaurant Macro F1: 0.7929. Result ID: 69908e843a6c314849017060.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f041e209131cea43478.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b7f1e209131cea2e981.md>)

[Implementation](<https://github.com/ZixuanKe/PyContinual>)

Recorded evaluation configuration: {"Category":"CL DAP-train","Model":"HAT-Adapter"}. This record does not assert independent reproduction.

### DAP-Prompt

Restaurant Macro F1: 0.79. Result ID: 69908e843a6c314849017055.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f041e209131cea43478.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6aa51e209131cea296c9.md>)

Recorded evaluation configuration: {"Category":"Non-CL","Model":"DAP-Prompt"}. This record does not assert independent reproduction.

### BCL

Restaurant Macro F1: 0.7897. Result ID: 69908e843a6c314849017059.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f041e209131cea43478.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b7f1e209131cea2e981.md>)

[Implementation](<https://github.com/ZixuanKe/PyContinual>)

Recorded evaluation configuration: {"Category":"CL DAP-train","Model":"BCL"}. This record does not assert independent reproduction.

### KD

Restaurant Macro F1: 0.7805. Result ID: 69908e843a6c31484901705b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f041e209131cea43478.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa61b81e209131ce9f5b87.md>)

Recorded evaluation configuration: {"Category":"CL DAP-train","Model":"KD"}. This record does not assert independent reproduction.

### HAT

Restaurant Macro F1: 0.7642. Result ID: 69908e843a6c31484901705e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f041e209131cea43478.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64681e209131cea0485c.md>)

[Implementation](<https://github.com/joansj/hat>)

Recorded evaluation configuration: {"Category":"CL DAP-train","Model":"HAT"}. This record does not assert independent reproduction.

### HAT-All

Restaurant Macro F1: 0.7494. Result ID: 69908e843a6c31484901705f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f041e209131cea43478.md>)

Recorded evaluation configuration: {"Category":"CL DAP-train","Model":"HAT-All"}. This record does not assert independent reproduction.

### EWC

Restaurant Macro F1: 0.7117. Result ID: 69908e843a6c31484901705c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f041e209131cea43478.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68a11e209131cea1d3e2.md>)

[Implementation](<https://github.com/aimagelab/mammoth>)

Recorded evaluation configuration: {"Category":"CL DAP-train","Model":"EWC"}. This record does not assert independent reproduction.

### DER++

Restaurant Macro F1: 0.6396. Result ID: 69908e843a6c31484901705d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f041e209131cea43478.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68a11e209131cea1d3e2.md>)

[Implementation](<https://github.com/aimagelab/mammoth>)

Recorded evaluation configuration: {"Category":"CL DAP-train","Model":"DER++"}. This record does not assert independent reproduction.

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