SCENE：使用软反事实验证可解释人工智能技术
SCENE: Evaluating Explainable AI Techniques Using Soft Counterfactuals
AI总结：
针对现有XAI方法不稳定易误导的问题，提出基于LLM零样本生成软反事实的SCENE评估方法，用两项指标评估文本分类任务中模型无关XAI方法的效果，为不同架构下XAI技术的优劣提供参考。
摘要：
可解释人工智能（XAI）在提升AI模型的透明度与问责性方面发挥着关键作用，尤其是在自然语言处理（NLP）任务中。然而，目前流行的XAI方法如LIME和SHAP已被发现存在不稳定性且可能产生误导，这凸显了标准化评估方法的必要性。本文提出SCENE（自然语言可解释性软反事实评估），这是一种新颖的评估方法，利用大语言模型（LLMs）以零样本方式生成软反事实解释。通过聚焦基于词元的替换，SCENE无需大量微调即可生成符合语境且语义有意义的软反事实。SCENE采用Validitysoft和Csoft指标来评估模型无关的XAI方法在文本分类任务中的有效性。将其应用于CNN、RNN和Transformer架构后，SCENE为各类XAI技术的优势与局限性提供了宝贵见解。
英文摘要：
Explainable Artificial Intelligence (XAI) plays a crucial role in enhancing the transparency and accountability of AI models, particularly in natural language processing (NLP) tasks. However, popular XAI methods such as LIME and SHAP have been found to be unstable and potentially misleading, underscoring the need for a standardized evaluation approach. This paper introduces SCENE (Soft Counterfactual Evaluation for Natural language Explainability), a novel evaluation method that leverages large language models (LLMs) to generate Soft Counterfactual explanations in a zero-shot manner. By focusing on token-based substitutions, SCENE creates contextually appropriate and semantically meaningful Soft Counterfactuals without extensive fine-tuning. SCENE adopts Validitysoft and Csoft metrics to assess the effectiveness of model-agnostic XAI methods in text classification tasks. Applied to CNN, RNN, and Transformer architectures, SCENE provides valuable insights into the strengths and limitations of various XAI techniques.
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。
