从内部探测LLM幻觉：基于内部知识的扰动驱动方法
Probing LLM Hallucination from Within: Perturbation-Driven Approach via Internal Knowledge
AI总结：
针对LLM幻觉检测依赖外部资源且未区分幻觉类型的问题，提出无需外部知识或训练的SHINE方法，通过扰动提示中的关键实体来探测对齐、未对齐和捏造三类幻觉，在多个数据集和模型上达到SOTA性能。
摘要：
LLM幻觉（即生成不忠实的文本）对LLM的实际应用构成了关键挑战。当前的检测方法通常依赖外部知识、LLM微调，或使用大量幻觉标注数据集进行监督训练。此外，这些方法未区分不同类型的幻觉，而这对提升检测性能至关重要。为解决这些局限性，我们引入了幻觉探测这一新任务，将LLM生成的文本分为三类：对齐、未对齐和捏造。基于我们的新发现，即扰动提示中的关键实体对LLM生成这三类文本的影响不同，我们提出了SHINE，一种无需外部知识、监督训练或LLM微调的新型幻觉探测方法。SHINE在三种现代LLM的幻觉探测中均有效，并在幻觉检测中达到最先进水平，在四个数据集和四个LLM上优于七种竞争方法，凸显了准确探测的重要性。
英文摘要：
LLM hallucination, where unfaithful text is generated, presents a critical challenge for LLMs' practical applications. Current detection methods often resort to external knowledge, LLM fine-tuning, or supervised training with large hallucination-labeled datasets. Moreover, these approaches do not distinguish between different types of hallucinations, which is crucial for enhancing detection performance. To address such limitations, we introduce hallucination probing, a new task that classifies LLM-generated text into three categories: aligned, misaligned, and fabricated. Driven by our novel discovery that perturbing key entities in prompts affects LLM's generation of these three types of text differently, we propose SHINE, a novel hallucination probing method that does not require external knowledge, supervised training, or LLM fine-tuning. SHINE is effective in hallucination probing across three modern LLMs, and achieves state-of-the-art performance in hallucination detection, outperforming seven competing methods across four datasets and four LLMs, underscoring the importance of probing for accurate detection.
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。
