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.

翻译：大型语言模型（LLMs）中存在的社会偏见已成为人工智能研究中的重要关切。这些通常嵌入训练数据中的偏见可能固化有害刻板印象并扭曲决策过程。当LLMs被整合到排序系统中时，它们可能传播这些偏见，导致搜索引擎和推荐系统等关键应用中出现不公正结果。与将文本序列视为整体结构的传统基于Transformer的模型不同，背包语言模型通过加权组合非上下文、已学习的词方面（亦称词义）来生成输出。利用这一架构，我们提出了一种用于去偏排序任务的框架。实验结果表明，该框架能有效缓解文本检索与排序中的性别偏见，且性能下降幅度极小。