不改提示词也不微调，直接定位并干预模型中偏见神经元。
Bi-directional Bias Attribution: Debiasing Large Language Models without Modifying Prompts
- 通过对比不同群体的用词，识别诱发刻板印象的词汇。
- 用积分梯度法定位具体偏见神经元，干预其投影层激活值。
- 三款主流大模型上有效降偏见，且不影响整体性能。
大型语言模型在多种自然语言处理任务中表现出色，但输出常含社会偏见，引发公平性担忧。现有去偏方法如数据微调或提示工程存在可扩展性差或影响多轮交互体验的问题。为此，我们提出一种无需微调或修改提示词的框架，用于检测诱发刻板印象的词汇并定位模型中的神经元级偏见。该框架首先通过跨人群对比分析，识别诱发刻板印象的形容词和名词；接着基于积分梯度的两种策略，将偏见行为归因至特定神经元；最后在投影层直接干预这些神经元的激活值以缓解偏见。在三个广泛使用的大型语言模型上的实验表明，该方法能有效降低偏见，同时保持模型整体性能。代码已开源：https://github.com/XMUDeepLIT/Bi-directional-Bias-Attribution。
原文摘要 · Abstract (English)
Large language models (LLMs) have demonstrated impressive capabilities across a wide range of natural language processing tasks. However, their outputs often exhibit social biases, raising fairness concerns. Existing debiasing methods, such as fine-tuning on additional datasets or prompt engineering, face scalability issues or compromise user experience in multi-turn interactions. To address these challenges, we propose a framework for detecting stereotype-inducing words and attributing neuron-level bias in LLMs, without the need for fine-tuning or prompt modification. Our framework first identifies stereotype-inducing adjectives and nouns via comparative analysis across demographic groups. We then attribute biased behavior to specific neurons using two attribution strategies based on integrated gradients. Finally, we mitigate bias by directly intervening on their activations at the projection layer. Experiments on three widely used LLMs demonstrate that our method effectively reduces bias while preserving overall model performance. Code is available at the github link: https://github.com/XMUDeepLIT/Bi-directional-Bias-Attribution.
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。