可解释人工智能（XAI）：从固有可解释性到大语言模型
Explainable artificial intelligence (XAI): from inherent explainability to large language models
AI总结：
本文是一篇可解释人工智能（XAI）领域的综述，梳理了从固有可解释模型到大语言模型等黑盒模型的XAI方法，介绍了利用大语言模型和视觉-语言模型提升可解释性的技术，对比了前沿方法的优劣，并指出了该领域的挑战与未来方向。
摘要：
近年来，人工智能（AI）持续取得巨大成功。然而，这些框架的决策逻辑往往不透明，导致利益相关者难以理解、解读或解释其行为。这一局限性削弱了人们对机器学习系统的信任，也使得这类系统在实际应用（尤其是医疗保健、自动驾驶等关键任务领域）的推广普遍受阻。可解释人工智能（XAI）技术可提升机器学习模型的可解释性或可解读性，让用户能够弄清决策的依据，还有可能规避不良行为。\n本综述全面梳理了可解释人工智能方法的发展历程，涵盖从固有可解释模型，到为包括大语言模型（LLM）在内的各类黑盒模型实现可解释性的现代方法。此外，本文还综述了利用大语言模型（LLM）和视觉-语言模型（VLM）框架来自动化或提升其他机器学习模型可解释性的XAI技术。将LLM和VLM用作可解释性方法，尤其能为模型的决策和行为提供高层、具备语义意义的解释。\n全文梳理了当前前沿方法的科学原理、优势与不足，并列出了不同的改进方向。在合适的位置，本文还呈现了各类方法的定性与定量比较结果，以展示它们的优劣对比。最后，本文讨论了XAI领域的核心挑战与未来研究方向。
英文摘要：
Artificial Intelligence (AI) has continued to achieve tremendous success in recent times. However, the decision logic of these frameworks is often not transparent, making it difficult for stakeholders to understand, interpret or explain their behavior. This limitation hinders trust in machine learning systems and causes a general reluctance towards their adoption in practical applications, particularly in mission-critical domains like healthcare and autonomous driving. Explainable AI (XAI) techniques facilitate the explainability or interpretability of machine learning models, enabling users to discern the basis of the decision and possibly avert undesirable behavior. This comprehensive survey details the advancements of explainable AI methods, from inherently interpretable models to modern approaches for achieving interpretability of various black box models, including large language models (LLMs). Additionally, we review explainable AI techniques that leverage LLM and vision-language model (VLM) frameworks to automate or improve the explainability of other machine learning models. The use of LLM and VLM as interpretability methods particularly enables high-level, semantically meaningful explanations of model decisions and behavior. Throughout the paper, we highlight the scientific principles, strengths and weaknesses of state-of-the-art methods and outline different areas of improvement. Where appropriate, we also present qualitative and quantitative comparison results of various methods to show how they compare. Finally, we discuss the key challenges of XAI and directions for future research.
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。
