LANCET: 通过结构熵进行神经干预以缓解大语言模型中的忠实幻觉
LANCET: Neural Intervention via Structural Entropy for Mitigating Faithfulness Hallucinations in LLMs
AI总结：
Lancet通过结构熵和幻觉差异比率实现精确神经干预，有效缓解大语言模型中的忠实幻觉问题。
摘要：
大型语言模型已经革新了信息处理，但其可靠性严重受到忠实幻觉的破坏。尽管当前方法试图通过节点级调整或粗略压制来缓解这一问题，但它们往往忽视了神经信息的分布式特性，导致干预不精确。认识到幻觉通过特定的正向传输路径传播，就像感染一样，我们旨在利用精确的结构分析来手术性地阻断这种流动。为此，我们提出了Lancet，一个新颖的框架，通过利用结构熵和幻觉差异比率实现精确的神经干预。Lancet首先通过梯度驱动的对比分析定位易产生幻觉的神经元，然后通过最小化结构熵来映射其传播路径，最后实施一种分层干预策略，以保持一般模型能力。在幻觉基准数据集上的全面评估表明，Lancet在很大程度上优于最先进的方法，验证了我们手术性神经干预方法的有效性。
英文摘要：
Large Language Models have revolutionized information processing, yet their reliability is severely compromised by faithfulness hallucinations. While current approaches attempt to mitigate this issue through node-level adjustments or coarse suppression, they often overlook the distributed nature of neural information, leading to imprecise interventions. Recognizing that hallucinations propagate through specific forward transmission pathways like an infection, we aim to surgically block this flow using precise structural analysis. To leverage this, we propose Lancet, a novel framework that achieves precise neural intervention by leveraging structural entropy and hallucination difference ratios. Lancet first locates hallucination-prone neurons via gradient-driven contrastive analysis, then maps their propagation pathways by minimizing structural entropy, and finally implements a hierarchical intervention strategy that preserves general model capabilities. Comprehensive evaluations across hallucination benchmark datasets demonstrate that Lancet significantly outperforms state-of-the-art methods, validating the effectiveness of our surgical approach to neural intervention.
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。
