让大模型回答敏感问题更公平，通过自适应提示消除偏见
DeCAP: Context-Adaptive Prompt Generation for Debiasing Zero-shot Question Answering in Large Language Models
- 根据问题模糊性动态生成去偏提示
- 在8个大模型上实现最优去偏问答效果
- 适合需要公平性的智能问答系统
尽管大语言模型（LLMs）在零样本问答（QA）中表现优异，但在面对社会敏感问题时，其内部知识会暴露偏见，导致性能下降。现有零样本方法高效但忽视上下文，无法阻止偏见传播。为此，我们提出DeCAP，一种基于上下文自适应提示生成的去偏方法。DeCAP利用问题模糊性检测，根据上下文采取相应去偏措施，并通过中立答案引导生成，抑制模型基于内部知识做出主观判断，从而最小化偏见传播。我们在八个LLMs上的实验表明，DeCAP实现了当前最优的零样本去偏问答性能，验证了其在多样化问答场景中提升模型公平性与准确性的有效性。
原文摘要 · Abstract (English)
While Large Language Models (LLMs) excel in zero-shot Question Answering (QA), they tend to expose biases in their internal knowledge when faced with socially sensitive questions, leading to a degradation in performance. Existing zero-shot methods are efficient but fail to consider context and prevent bias propagation in the answers. To address this, we propose DeCAP, a method for debiasing LLMs using Context-Adaptive Prompt Generation. DeCAP leverages a Question Ambiguity Detection to take appropriate debiasing actions based on the context and a Neutral Answer Guidance Generation to suppress the LLMs make objective judgments about the context, minimizing the propagation of bias from their internal knowledge. Our various experiments across eight LLMs show that DeCAP achieves state-of-the-art zero-shot debiased QA performance. This demonstrates DeCAP's efficacy in enhancing the fairness and accuracy of LLMs in diverse QA settings.
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。