# Response Safety on JailBreakV-28K (avg)

Source: [Response Safety on JailBreakV-28K (avg)](<https://www.sota2.com/research/sota/response-safety-on-jailbreakv-28k-avg>)

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

Data updated: 2026-04-13T08:09:45.874Z

Evaluation of model response safety performance using the JailBreakV-28K (average) dataset, measured by JBV-R and JBV-QG 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 | Response Safety |
| Dataset (including any stated split) | JailBreakV-28K (avg) |
| Metric | JBV-R Score |
| Unit | SCALAR |
| 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

- [JBV-R Score](<https://www.sota2.com/research/sota/response-safety-on-jailbreakv-28k-avg.md?metric=JBV-R%20Score>): Higher is better; unit: SCALAR.

- [JBV-QG Score](<https://www.sota2.com/research/sota/response-safety-on-jailbreakv-28k-avg.md?metric=JBV-QG%20Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | JBV-R Score | Result date | Report paper |
| --- | --- | --- | --- |
| DACO | 0.975 | Not recorded | 69dc78987d0172140ec78ba3 |
| MOP \[56\] | 0.917 | Not recorded | 69dc78987d0172140ec78ba3 |
| DACO | 0.903 | Not recorded | 69dc78987d0172140ec78ba3 |
| DACO | 0.885 | Not recorded | 69dc78987d0172140ec78ba3 |
| ActAdd \[50, 101, 134\] | 0.86 | Not recorded | 69dc78987d0172140ec78ba3 |
| MOP \[56\] | 0.835 | Not recorded | 69dc78987d0172140ec78ba3 |
| MOP \[56\] | 0.811 | Not recorded | 69dc78987d0172140ec78ba3 |
| Prompting \[52\] | 0.809 | Not recorded | 69dc78987d0172140ec78ba3 |
| ActAdd \[50, 101, 134\] | 0.783 | Not recorded | 69dc78987d0172140ec78ba3 |
| No Steering | 0.73 | Not recorded | 69dc78987d0172140ec78ba3 |
| ActAdd \[50, 101, 134\] | 0.691 | Not recorded | 69dc78987d0172140ec78ba3 |
| Prompting \[52\] | 0.659 | Not recorded | 69dc78987d0172140ec78ba3 |
| No Steering | 0.564 | Not recorded | 69dc78987d0172140ec78ba3 |
| Prompting \[52\] | 0.471 | Not recorded | 69dc78987d0172140ec78ba3 |
| No Steering | 0.303 | Not recorded | 69dc78987d0172140ec78ba3 |

### DACO

JBV-R Score: 0.975. Result ID: 69dca36d47f34ce924c37146.

[Reporting paper](<https://www.sota2.com/research/paper/69dc78987d0172140ec78ba3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69dc78987d0172140ec78ba3.md>)

Recorded evaluation configuration: {"Target Model":"InternVL3.5-8B-Instruct \[108\]","Steering Method":"DACO (Ours)"}. This record does not assert independent reproduction.

### MOP \[56\]

JBV-R Score: 0.917. Result ID: 69dca36d47f34ce924c37145.

[Reporting paper](<https://www.sota2.com/research/paper/69dc78987d0172140ec78ba3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75881e209131cea686ad.md>)

[Implementation](<https://github.com/peterljq/Parsimonious-Concept-Engineering>)

Recorded evaluation configuration: {"Target Model":"InternVL3.5-8B-Instruct \[108\]","Steering Method":"MOP \[56\]"}. This record does not assert independent reproduction.

### DACO

JBV-R Score: 0.903. Result ID: 69dca36d47f34ce924c3713c.

[Reporting paper](<https://www.sota2.com/research/paper/69dc78987d0172140ec78ba3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69dc78987d0172140ec78ba3.md>)

Recorded evaluation configuration: {"Target Model":"Qwen2.5-VL-7B-Instruct \[5\]","Steering Method":"DACO (Ours)"}. This record does not assert independent reproduction.

### DACO

JBV-R Score: 0.885. Result ID: 69dca36d47f34ce924c37141.

[Reporting paper](<https://www.sota2.com/research/paper/69dc78987d0172140ec78ba3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69dc78987d0172140ec78ba3.md>)

Recorded evaluation configuration: {"Target Model":"LLaVA1.6-Mistral-7B \[48\]","Steering Method":"DACO (Ours)"}. This record does not assert independent reproduction.

### ActAdd \[50, 101, 134\]

JBV-R Score: 0.86. Result ID: 69dca36d47f34ce924c37144.

[Reporting paper](<https://www.sota2.com/research/paper/69dc78987d0172140ec78ba3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa754e1e209131cea66fd9.md>)

Recorded evaluation configuration: {"Target Model":"InternVL3.5-8B-Instruct \[108\]","Steering Method":"ActAdd \[50, 101, 134\]"}. This record does not assert independent reproduction.

### MOP \[56\]

JBV-R Score: 0.835. Result ID: 69dca36d47f34ce924c3713b.

[Reporting paper](<https://www.sota2.com/research/paper/69dc78987d0172140ec78ba3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75881e209131cea686ad.md>)

[Implementation](<https://github.com/peterljq/Parsimonious-Concept-Engineering>)

Recorded evaluation configuration: {"Target Model":"Qwen2.5-VL-7B-Instruct \[5\]","Steering Method":"MOP \[56\]"}. This record does not assert independent reproduction.

### MOP \[56\]

JBV-R Score: 0.811. Result ID: 69dca36d47f34ce924c37140.

[Reporting paper](<https://www.sota2.com/research/paper/69dc78987d0172140ec78ba3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75881e209131cea686ad.md>)

[Implementation](<https://github.com/peterljq/Parsimonious-Concept-Engineering>)

Recorded evaluation configuration: {"Target Model":"LLaVA1.6-Mistral-7B \[48\]","Steering Method":"MOP \[56\]"}. This record does not assert independent reproduction.

### Prompting \[52\]

JBV-R Score: 0.809. Result ID: 69dca36d47f34ce924c37143.

[Reporting paper](<https://www.sota2.com/research/paper/69dc78987d0172140ec78ba3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73c11e209131cea5e455.md>)

Recorded evaluation configuration: {"Target Model":"InternVL3.5-8B-Instruct \[108\]","Steering Method":"Prompting \[52\]"}. This record does not assert independent reproduction.

### ActAdd \[50, 101, 134\]

JBV-R Score: 0.783. Result ID: 69dca36d47f34ce924c3713f.

[Reporting paper](<https://www.sota2.com/research/paper/69dc78987d0172140ec78ba3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa754e1e209131cea66fd9.md>)

Recorded evaluation configuration: {"Target Model":"LLaVA1.6-Mistral-7B \[48\]","Steering Method":"ActAdd \[50, 101, 134\]"}. This record does not assert independent reproduction.

### No Steering

JBV-R Score: 0.73. Result ID: 69dca36d47f34ce924c37142.

[Reporting paper](<https://www.sota2.com/research/paper/69dc78987d0172140ec78ba3.md>)

Recorded evaluation configuration: {"Target Model":"InternVL3.5-8B-Instruct \[108\]","Steering Method":"No Steering"}. This record does not assert independent reproduction.

### ActAdd \[50, 101, 134\]

JBV-R Score: 0.691. Result ID: 69dca36d47f34ce924c3713a.

[Reporting paper](<https://www.sota2.com/research/paper/69dc78987d0172140ec78ba3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa754e1e209131cea66fd9.md>)

Recorded evaluation configuration: {"Target Model":"Qwen2.5-VL-7B-Instruct \[5\]","Steering Method":"ActAdd \[50, 101, 134\]"}. This record does not assert independent reproduction.

### Prompting \[52\]

JBV-R Score: 0.659. Result ID: 69dca36d47f34ce924c37139.

[Reporting paper](<https://www.sota2.com/research/paper/69dc78987d0172140ec78ba3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73c11e209131cea5e455.md>)

Recorded evaluation configuration: {"Target Model":"Qwen2.5-VL-7B-Instruct \[5\]","Steering Method":"Prompting \[52\]"}. This record does not assert independent reproduction.

### No Steering

JBV-R Score: 0.564. Result ID: 69dca36d47f34ce924c37138.

[Reporting paper](<https://www.sota2.com/research/paper/69dc78987d0172140ec78ba3.md>)

Recorded evaluation configuration: {"Target Model":"Qwen2.5-VL-7B-Instruct \[5\]","Steering Method":"No Steering"}. This record does not assert independent reproduction.

### Prompting \[52\]

JBV-R Score: 0.471. Result ID: 69dca36d47f34ce924c3713e.

[Reporting paper](<https://www.sota2.com/research/paper/69dc78987d0172140ec78ba3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73c11e209131cea5e455.md>)

Recorded evaluation configuration: {"Target Model":"LLaVA1.6-Mistral-7B \[48\]","Steering Method":"Prompting \[52\]"}. This record does not assert independent reproduction.

### No Steering

JBV-R Score: 0.303. Result ID: 69dca36d47f34ce924c3713d.

[Reporting paper](<https://www.sota2.com/research/paper/69dc78987d0172140ec78ba3.md>)

Recorded evaluation configuration: {"Target Model":"LLaVA1.6-Mistral-7B \[48\]","Steering Method":"No Steering"}. This record does not assert independent reproduction.

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