# Refusal Detection on XSTest Refusal OOD (test) Source: [Refusal Detection on XSTest Refusal OOD (test)]() Collection index: [llms.txt]() Data updated: 2026-05-12T06:40:08.647Z Evaluation of model performance on Refusal Detection using the test split of the XSTest Refusal Out-of-Distribution (OOD) dataset, reporting metrics like MC Recall and BC AUROC. 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 | Refusal Detection | | Dataset (including any stated split) | XSTest Refusal OOD (test) | | Metric | MC Recall | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 7 of 7 | | 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 - [MC Recall](): Higher is better; unit: PERCENT. - [BC AUROC](): Higher is better; unit: PERCENT. ## Recorded results | Method | MC Recall | Result date | Report paper | | --- | --- | --- | --- | | ACS Refusal Probe | 100 | Not recorded | 6a02b48edbc836b87d824cd0 | | ACS Refusal Probe | 99 | Not recorded | 6a02b48edbc836b87d824cd0 | | ACS Refusal Probe | 99 | Not recorded | 6a02b48edbc836b87d824cd0 | | ACS Refusal Probe | 99 | Not recorded | 6a02b48edbc836b87d824cd0 | | ACS Refusal Probe | 99 | Not recorded | 6a02b48edbc836b87d824cd0 | | ACS Refusal Probe | 98 | Not recorded | 6a02b48edbc836b87d824cd0 | | ACS Refusal Probe | 97 | Not recorded | 6a02b48edbc836b87d824cd0 | ### ACS Refusal Probe MC Recall: 100. Result ID: 6a02ca7f47f34ce924e4f664. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target Model":"Phi"}. This record does not assert independent reproduction. ### ACS Refusal Probe MC Recall: 99. Result ID: 6a02ca7f47f34ce924e4f661. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target Model":"Llama"}. This record does not assert independent reproduction. ### ACS Refusal Probe MC Recall: 99. Result ID: 6a02ca7f47f34ce924e4f662. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target Model":"Qwen"}. This record does not assert independent reproduction. ### ACS Refusal Probe MC Recall: 99. Result ID: 6a02ca7f47f34ce924e4f666. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target Model":"LQMP (4-fam)"}. This record does not assert independent reproduction. ### ACS Refusal Probe MC Recall: 99. Result ID: 6a02ca7f47f34ce924e4f667. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target Model":"LQMPG (5-fam)"}. This record does not assert independent reproduction. ### ACS Refusal Probe MC Recall: 98. Result ID: 6a02ca7f47f34ce924e4f663. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target Model":"Mistral"}. This record does not assert independent reproduction. ### ACS Refusal Probe MC Recall: 97. Result ID: 6a02ca7f47f34ce924e4f665. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target Model":"Gemma"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.