# Gendered-term mention ratio control on GCGender Source: [Gendered-term mention ratio control on GCGender]() Collection index: [llms.txt]() Data updated: 2026-06-01T08:04:25.455Z Evaluation of a model's ability to control the ratio of gendered-term mentions (M, F, N) within generated text using the GCGender dataset. 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 | Gendered-term mention ratio control | | Dataset (including any stated split) | GCGender | | Metric | Delta M Mention Ratio | | Unit | SCALAR | | Direction | Lower is better | | Results loaded | 18 of 18 | | 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 - [Delta M Mention Ratio](): Lower is better; unit: SCALAR. - [Delta F Mention Ratio](): Lower is better; unit: SCALAR. - [Delta N Mention Ratio](): Lower is better; unit: SCALAR. ## Recorded results | Method | Delta M Mention Ratio | Result date | Report paper | | --- | --- | --- | --- | | sNeuron-TST | -0.92 | Not recorded | 6a1d1213dbd7150506f83fef | | sNeuron-TST | -0.83 | Not recorded | 6a1d1213dbd7150506f83fef | | LAPE | -0.62 | Not recorded | 6a1d1213dbd7150506f83fef | | LAPE | -0.57 | Not recorded | 6a1d1213dbd7150506f83fef | | LAPE | -0.06 | Not recorded | 6a1d1213dbd7150506f83fef | | neuron-level intervention approach | -0.02 | Not recorded | 6a1d1213dbd7150506f83fef | | LAPE | -0.02 | Not recorded | 6a1d1213dbd7150506f83fef | | neuron-level intervention approach | -0.02 | Not recorded | 6a1d1213dbd7150506f83fef | | neuron-level intervention approach | -0.01 | Not recorded | 6a1d1213dbd7150506f83fef | | LAPE | 0 | Not recorded | 6a1d1213dbd7150506f83fef | | neuron-level intervention approach | 0 | Not recorded | 6a1d1213dbd7150506f83fef | | sNeuron-TST | 0.02 | Not recorded | 6a1d1213dbd7150506f83fef | | LAPE | 0.02 | Not recorded | 6a1d1213dbd7150506f83fef | | sNeuron-TST | 0.04 | Not recorded | 6a1d1213dbd7150506f83fef | | neuron-level intervention approach | 0.06 | Not recorded | 6a1d1213dbd7150506f83fef | | sNeuron-TST | 0.24 | Not recorded | 6a1d1213dbd7150506f83fef | | neuron-level intervention approach | 0.76 | Not recorded | 6a1d1213dbd7150506f83fef | | sNeuron-TST | 2.45 | Not recorded | 6a1d1213dbd7150506f83fef | ### sNeuron-TST Delta M Mention Ratio: -0.92. Result ID: 6a1d3c4cfbc373592c163a00. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Llama 3.1","Target":"Masculine"}. This record does not assert independent reproduction. ### sNeuron-TST Delta M Mention Ratio: -0.83. Result ID: 6a1d3c4cfbc373592c1639f7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen 2.5","Target":"Masculine"}. This record does not assert independent reproduction. ### LAPE Delta M Mention Ratio: -0.62. Result ID: 6a1d3c4cfbc373592c163a01. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"Llama 3.1","Target":"Masculine"}. This record does not assert independent reproduction. ### LAPE Delta M Mention Ratio: -0.57. Result ID: 6a1d3c4cfbc373592c1639f8. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"Qwen 2.5","Target":"Masculine"}. This record does not assert independent reproduction. ### LAPE Delta M Mention Ratio: -0.06. Result ID: 6a1d3c4cfbc373592c1639f5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"Qwen 2.5","Target":"Feminine"}. This record does not assert independent reproduction. ### neuron-level intervention approach Delta M Mention Ratio: -0.02. Result ID: 6a1d3c4cfbc373592c1639fc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen 2.5","Target":"Neutral"}. This record does not assert independent reproduction. ### LAPE Delta M Mention Ratio: -0.02. Result ID: 6a1d3c4cfbc373592c1639fe. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"Llama 3.1","Target":"Feminine"}. This record does not assert independent reproduction. ### neuron-level intervention approach Delta M Mention Ratio: -0.02. Result ID: 6a1d3c4cfbc373592c1639ff. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Llama 3.1","Target":"Feminine"}. This record does not assert independent reproduction. ### neuron-level intervention approach Delta M Mention Ratio: -0.01. Result ID: 6a1d3c4cfbc373592c1639f6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen 2.5","Target":"Feminine"}. This record does not assert independent reproduction. ### LAPE Delta M Mention Ratio: 0. Result ID: 6a1d3c4cfbc373592c1639fb. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"Qwen 2.5","Target":"Neutral"}. This record does not assert independent reproduction. ### neuron-level intervention approach Delta M Mention Ratio: 0. Result ID: 6a1d3c4cfbc373592c163a05. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Llama 3.1","Target":"Neutral"}. This record does not assert independent reproduction. ### sNeuron-TST Delta M Mention Ratio: 0.02. Result ID: 6a1d3c4cfbc373592c1639f4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen 2.5","Target":"Feminine"}. This record does not assert independent reproduction. ### LAPE Delta M Mention Ratio: 0.02. Result ID: 6a1d3c4cfbc373592c163a04. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"Llama 3.1","Target":"Neutral"}. This record does not assert independent reproduction. ### sNeuron-TST Delta M Mention Ratio: 0.04. Result ID: 6a1d3c4cfbc373592c163a03. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Llama 3.1","Target":"Neutral"}. This record does not assert independent reproduction. ### neuron-level intervention approach Delta M Mention Ratio: 0.06. Result ID: 6a1d3c4cfbc373592c1639f9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen 2.5","Target":"Masculine"}. This record does not assert independent reproduction. ### sNeuron-TST Delta M Mention Ratio: 0.24. Result ID: 6a1d3c4cfbc373592c1639fa. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen 2.5","Target":"Neutral"}. This record does not assert independent reproduction. ### neuron-level intervention approach Delta M Mention Ratio: 0.76. Result ID: 6a1d3c4cfbc373592c163a02. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Llama 3.1","Target":"Masculine"}. This record does not assert independent reproduction. ### sNeuron-TST Delta M Mention Ratio: 2.45. Result ID: 6a1d3c4cfbc373592c1639fd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Llama 3.1","Target":"Feminine"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.