用背包架构减少检索中的性别偏见，效果好且不影响性能。
Controlling Gender Bias in Retrieval via a Backpack Architecture
- 基于背包语言模型，将词义拆解为非上下文的可学习方面。
- 在多个检索任务中显著降低性别偏见，性能损失极小。
- 适合关注公平性与推荐系统优化的研究者与工程师。
大型语言模型（LLM）中存在的社会偏见已成为人工智能研究的重要关切。这些偏见通常源于训练数据，可能强化有害刻板印象并扭曲决策过程。当LLM被集成到排序系统中时，会传播此类偏见，导致搜索引擎和推荐系统等关键应用出现不公平结果。背包语言模型（Backpack Language Models）不同于传统Transformer模型将文本序列视为整体结构的方式，而是将输出生成为非上下文、可学习词义方面（即“语义”）的加权组合。基于该架构，我们提出了一种用于消除排序任务中偏见的框架。实验表明，该框架能有效缓解文本检索与排序中的性别偏见，同时性能下降微乎其微。
原文摘要 · Abstract (English)
The presence of social biases in large language models (LLMs) has become a significant concern in AI research. These biases, often embedded in training data, can perpetuate harmful stereotypes and distort decision-making processes. When LLMs are integrated into ranking systems, they can propagate these biases, leading to unfair outcomes in critical applications such as search engines and recommendation systems. Backpack Language Models, unlike traditional transformer-based models that treat text sequences as monolithic structures, generate outputs as weighted combinations of non-contextual, learned word aspects, also known as senses. Leveraging this architecture, we propose a framework for debiasing ranking tasks. Our experimental results show that this framework effectively mitigates gender bias in text retrieval and ranking with minimal degradation in performance.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。