# Gender Controlled Generation on InclusiveGender (Neutral) Source: [Gender Controlled Generation on InclusiveGender (Neutral)]() Collection index: [llms.txt]() Data updated: 2026-06-01T08:04:25.550Z Evaluation of model performance on the Neutral subset of the InclusiveGender dataset, focusing on controlling the generation of gendered terms and measuring associated mention ratios and deviations across male (M), female (F), and neutral (N) categories. 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 | Gender Controlled Generation | | Dataset (including any stated split) | InclusiveGender (Neutral) | | Metric | Avg Gendered Terms per Response (M) | | Unit | SCALAR | | Direction | Lower is better | | Results loaded | 4 of 4 | | 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 - [Avg Gendered Terms per Response (M)](): Lower is better; unit: SCALAR. - [Avg Gendered Terms per Response (F)](): Lower is better; unit: SCALAR. - [Avg Gendered Terms per Response (N)](): Lower is better; unit: SCALAR. - [Mention Ratio (%) (M)](): Lower is better; unit: PERCENT. - [Mention Ratio (%) (F)](): Lower is better; unit: PERCENT. - [Mention Ratio (%) (N)](): Lower is better; unit: PERCENT. - [Ratio Deviation (%) (M)](): Lower is better; unit: PERCENT. - [Ratio Deviation (%) (F)](): Lower is better; unit: PERCENT. - [Ratio Deviation (%) (N)](): Lower is better; unit: PERCENT. ## Recorded results | Method | Avg Gendered Terms per Response (M) | Result date | Report paper | | --- | --- | --- | --- | | LAPE | 0.09 | Not recorded | 6a1d1213dbd7150506f83fef | | Gender Neuron Masking (Ours) | 0.13 | Not recorded | 6a1d1213dbd7150506f83fef | | Baseline | 0.14 | Not recorded | 6a1d1213dbd7150506f83fef | | sNeuron-TST | 0.21 | Not recorded | 6a1d1213dbd7150506f83fef | ### LAPE Avg Gendered Terms per Response (M): 0.09. Result ID: 6a1d3c4cfbc373592c163a10. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Base Model":"Qwen 2.5"}. This record does not assert independent reproduction. ### Gender Neuron Masking (Ours) Avg Gendered Terms per Response (M): 0.13. Result ID: 6a1d3c4cfbc373592c163a11. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Qwen 2.5"}. This record does not assert independent reproduction. ### Baseline Avg Gendered Terms per Response (M): 0.14. Result ID: 6a1d3c4cfbc373592c163a0e. [Reporting paper]() Recorded evaluation configuration: {"Base Model":"Qwen 2.5"}. This record does not assert independent reproduction. ### sNeuron-TST Avg Gendered Terms per Response (M): 0.21. Result ID: 6a1d3c4cfbc373592c163a0f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Qwen 2.5"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.