这篇论文教你用剪枝定位偏见：最多剪40个神经元，Llama-3.2-1B能力保住99.49%，但偏见不是消失而是换了方向。
Fairness Pruning是一种轻量结构干预方法，用于定位大语言模型中的群体偏见。实验在Llama-3.2系列和Salamandra-2B等最大3B参数模型上进行，结合标准基准和定性生成测试。在Llama-3.2-1B上归零最多40个神经元（不到总MLP宽度的0.031%），推理和通用知识能力保留均值达99.49%。由于BiasScore无符号，候选集混合了促进和抑制刻板印象的神经元，干预导致双向偏见失稳。结果证实群体偏见处理与模型能力运行在可分离的电路上。
Fairness Pruning: Locating Demographic Bias in GLU-MLP Layers via Differential Activations
This work presents Fairness Pruning, a lightweight structural intervention method designed for the management and future mitigation of demographic bias in large language models (LLMs). As a foundational empirical validation of this method, this work focuses on causal bias localization. Using minimally contrastive prompt pairs and inference-time activation capture, the method identifies neurons that react differentially when processing demographic attributes in GLU architectures, evaluating the signal at the down_proj input. Empirical evaluation was conducted on models of up to 3 billion parameters (Llama-3.2 family and Salamandra-2B), combining standardized benchmark evaluation with qualitative text generation experiments. Results demonstrate that zeroing the identified neurons alters how the model responds to associated demographic variables. However, rather than producing flat mitigation, the intervention causes bidirectional bias destabilization: because BiasScore is unsigned, candidate sets mix neurons that push toward and against the stereotype, and the net effect on aggregate bias depends on which sign dominates. The intervention is extremely surgical: zeroing at most 40 neurons in Llama-3.2-1B (less than 0.031% of total MLP width) achieves a mean retention of 99.49% in reasoning and general knowledge capabilities. These findings empirically confirm that demographic bias processing and model capabilities operate on dissociable circuits, establishing the methodological foundations for transitioning from blind zeroing toward directional behavior modulation.