通过上下文注入缓解文本嵌入中的偏见，提升检索准确性。
On Debiasing Text Embeddings Through Context Injection
- 用上下文注入方法调节嵌入模型的偏见响应能力。
- 高精度模型更易捕捉偏见，但也能更好融入上下文信息。
- 新算法动态选择检索数量，精准召回性别与中性内容。
当前自然语言处理进展使得基于文本数据的应用成为可能，其核心依赖于将文本转化为向量表示的嵌入模型。然而，已有研究表明这些嵌入会捕捉并延续文本中的偏见。尽管已有若干去偏方法提出，但未充分利用现代嵌入模型在上下文理解方面的进步。本文通过量化19个嵌入模型的偏见程度及其对上下文注入的响应能力，填补了这一空白。结果显示，性能更高的模型更易捕获偏见，但也更善于融入上下文。令人意外的是，模型虽能轻松表达肯定语义，却难以表达中性语义。在检索任务中，我们发现嵌入中的偏见会导致非期望结果。基于这些新发现，我们设计了一种简单的top $k$ 检索算法，其中 $k$ 动态调整。实验表明，该算法能完全召回所有相关的性别化和中性文本块。
原文摘要 · Abstract (English)
Current advances in Natural Language Processing (NLP) have made it increasingly feasible to build applications leveraging textual data. Generally, the core of these applications rely on having a good semantic representation of text into vectors, via embedding models. However, it has been shown that these embeddings capture and perpetuate biases already present in text. While a few techniques have been proposed to debias embeddings, they do not take advantage of the recent advances in context understanding of modern embedding models. In this paper, we fill this gap by conducting a review of 19 embedding models by quantifying their biases and how well they respond to context injection as a mean of debiasing. We show that higher performing models are more prone to capturing biases, but are also better at incorporating context. Surprisingly, we find that while models can easily embed affirmative semantics, they fail at embedding neutral semantics. Finally, in a retrieval task, we show that biases in embeddings can lead to non-desirable outcomes. We use our new-found insights to design a simple algorithm for top $k$ retrieval, where $k$ is dynamically selected. We show that our algorithm is able to retrieve all relevant gendered and neutral chunks.
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。