Fairness Pruning: Locating Demographic Bias in GLU-MLP Layers via Differential Activations

  • 类型：arxiv
  • 标识：2607.28319
  • 链接：https://arxiv.org/abs/2607.28319
  • 主分类：evaluation
  • 形态：method
  • 被引：0
  • 被引来源：Semantic Scholar + OpenAlex
  • S2被引：0
  • OpenAlex被引：0
  • 影响力被引：0
  • TLDR：Empirical evaluation of Fairness Pruning 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.
  • OpenAlex ID：W7171947677
  • OpenAlex DOI：10.48550/arxiv.2607.28319
  • DOI：10.48550/arxiv.2607.28319
  • DOI来源：OpenAlex
  • 开放获取：green
  • 开放获取链接：https://doi.org/10.48550/arxiv.2607.28319
  • OpenAlex更新：2026-08-26
  • 待LLM分类：否
  • 标题中文：Fairness Pruning：通过差异激活定位 GLU-MLP 层中的人口统计偏差
  • TLDR中文：对 Fairness Pruning 的实证评估表明，群体偏置处理与模型能力运行在可分离的电路上，奠定了从盲目零化向定向行为调制过渡的方法论基础。
  • 来源文件：
  • /inbox/tom/_candidates/2026-07-31-agent-rag-longcontext-candidates.json
  • /inbox/tom/_candidates/2026-08-01-agent-rag-longcontext-candidates.json
  • /inbox/tom/_candidates/2026-08-02-agent-rag-longcontext-candidates.json
  • /inbox/tom/_candidates/2026-08-03-agent-rag-longcontext-candidates.json
  • /inbox/tom/_candidates/2026-08-03-agent-memory-tool-use-candidates.json
  • [S2 enrich]
  • [OpenAlex backfill]