# Text Classification on ToxiGen (test) Source: [Text Classification on ToxiGen (test)]() Collection index: [llms.txt]() Data updated: 2026-05-29T10:53:48.778Z Evaluation of general text classification performance on the test split of the ToxiGen dataset, reporting Accuracy and AUC. 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 | Text Classification | | Dataset (including any stated split) | ToxiGen (test) | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 12 of 12 | | 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](): Higher is better; unit: PERCENT. - [AUC](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | UNISTEER | 85 | Not recorded | 6a191de3dbd7150506f82bf4 | | UNISTEER | 82 | Not recorded | 6a191de3dbd7150506f82bf4 | | LoReFT | 80 | Not recorded | 6a191de3dbd7150506f82bf4 | | UNISTEER | 80 | Not recorded | 6a191de3dbd7150506f82bf4 | | LoReFT | 77 | Not recorded | 6a191de3dbd7150506f82bf4 | | LoReFT | 77 | Not recorded | 6a191de3dbd7150506f82bf4 | | RepE | 76 | Not recorded | 6a191de3dbd7150506f82bf4 | | CAA | 72 | Not recorded | 6a191de3dbd7150506f82bf4 | | CAA | 67 | Not recorded | 6a191de3dbd7150506f82bf4 | | CAA | 65 | Not recorded | 6a191de3dbd7150506f82bf4 | | RepE | 52 | Not recorded | 6a191de3dbd7150506f82bf4 | | RepE | 46 | Not recorded | 6a191de3dbd7150506f82bf4 | ### UNISTEER Accuracy: 85. Result ID: 6a196fdcfbc373592c148c63. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen2.5-7B"}. This record does not assert independent reproduction. ### UNISTEER Accuracy: 82. Result ID: 6a196fdcfbc373592c148c5f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen2.5-1.5B"}. This record does not assert independent reproduction. ### LoReFT Accuracy: 80. Result ID: 6a196fdcfbc373592c148c5a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Llama-3.2-1B"}. This record does not assert independent reproduction. ### UNISTEER Accuracy: 80. Result ID: 6a196fdcfbc373592c148c5b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Llama-3.2-1B"}. This record does not assert independent reproduction. ### LoReFT Accuracy: 77. Result ID: 6a196fdcfbc373592c148c5e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen2.5-1.5B"}. This record does not assert independent reproduction. ### LoReFT Accuracy: 77. Result ID: 6a196fdcfbc373592c148c62. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen2.5-7B"}. This record does not assert independent reproduction. ### RepE Accuracy: 76. Result ID: 6a196fdcfbc373592c148c5d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"Qwen2.5-1.5B"}. This record does not assert independent reproduction. ### CAA Accuracy: 72. Result ID: 6a196fdcfbc373592c148c60. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen2.5-7B"}. This record does not assert independent reproduction. ### CAA Accuracy: 67. Result ID: 6a196fdcfbc373592c148c5c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen2.5-1.5B"}. This record does not assert independent reproduction. ### CAA Accuracy: 65. Result ID: 6a196fdcfbc373592c148c58. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Llama-3.2-1B"}. This record does not assert independent reproduction. ### RepE Accuracy: 52. Result ID: 6a196fdcfbc373592c148c61. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"Qwen2.5-7B"}. This record does not assert independent reproduction. ### RepE Accuracy: 46. Result ID: 6a196fdcfbc373592c148c59. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"Llama-3.2-1B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.