面向大语言模型的因果可解释护栏
A Causal Explainable Guardrails for Large Language Models
AI总结：
本文提出LLMGuardrail框架，通过因果分析与对抗学习消除LLMs引导过程中的语义偏见，并提供可解释性，从而更安全可靠地引导模型输出符合期望属性。
摘要：
大语言模型（LLMs）在自然语言任务中展现出卓越性能，但其输出可能呈现不良属性或偏见。现有引导LLMs朝向期望属性的方法通常假设表征无偏，并仅依赖引导提示。然而，预训练所学表征可能引入语义偏见，影响引导过程，导致次优结果。我们提出LLMGuardrail，一个结合因果分析与对抗学习以获取LLMs中无偏引导表征的新框架。LLMGuardrail系统性地识别并阻断偏见的混杂效应，从而提取无偏引导表征。此外，该框架包含可解释组件，可洞察生成输出与期望方向之间的对齐情况。实验表明，LLMGuardrail在引导LLMs朝向期望属性的同时有效缓解偏见。我们的工作有助于开发符合期望属性的安全可靠LLMs。
英文摘要：
Large Language Models (LLMs) have shown impressive performance in natural language tasks, but their outputs can exhibit undesirable attributes or biases. Existing methods for steering LLMs toward desired attributes often assume unbiased representations and rely solely on steering prompts. However, the representations learned from pre-training can introduce semantic biases that influence the steering process, leading to suboptimal results. We propose LLMGuardrail, a novel framework that incorporates causal analysis and adversarial learning to obtain unbiased steering representations in LLMs. LLMGuardrail systematically identifies and blocks the confounding effects of biases, enabling the extraction of unbiased steering representations. Additionally, it includes an explainable component that provides insights into the alignment between the generated output and the desired direction. Experiments demonstrate LLMGuardrail's effectiveness in steering LLMs toward desired attributes while mitigating biases. Our work contributes to the development of safe and reliable LLMs that align with desired attributes.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
