用大模型生成可懂的网络解释，提升非专家理解力
Generative Explainability for Next-Generation Networks: LLM-Augmented XAI with Mutual Feature Interactions
- 用中等规模大模型+特征互作数据构造提示词
- 解释有用性和覆盖范围分别提升12.2%和6.2%
- 适合需要可解释性的网络运维人员
随着人工智能与机器学习模型在网络运维中的广泛应用，其缺乏透明性成为阻碍操作员信任的关键障碍。现有可解释人工智能（XAI）技术难以为非专业人士提供有效支持，生成的技术性输出难以转化为可操作洞察。本文提出一种专门应对该问题的框架，利用中等规模大语言模型，并超越传统SHAP特征影响值的使用方式。该框架通过包含特征互作信息的结构化提示，生成人类可理解的自然语言解释。为验证框架有效性，我们在光传输质量（QoT）估计任务上进行了实证评估，采用人工评估者进行独立评测，结果显示评估者间一致性高。相比仅使用原始SHAP值的前沿基线方法，本方案在解释有用性和范围上分别提升12.2%和6.2%，同时达到97.5%的正确率。
原文摘要 · Abstract (English)
As artificial intelligence and machine learning (AI/ML) models become integral to network operations, their lack of transparency poses a significant barrier to operator trust. Existing explainable artificial intelligence (XAI) techniques often fail to bridge this gap for non-specialists, producing technical outputs that are difficult to translate into actionable insights. This paper presents a framework specifically designed to address this shortcoming. It leverages a moderately sized large language model (LLM) and extends beyond the standard use of SHapley Additive exPlanations (SHAP) feature influence values. The framework employs a structured prompt enriched with mutual feature interaction data to generate human-understandable natural language explanations. To validate our framework, we performed an empirical evaluation on an optical quality of transmission (QoT) estimation use case with human evaluators. We collected independent performance evaluations from specialists, which showed a high inter-evaluator agreement. Compared to a state-of-the-art baseline that uses only SHAP feature influence values in a straightforward prompt, our approach improves the explanation usefulness and scope by 12.2% and 6.2%, while achieving 97.5% correctness.
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。