实践中的可解释性：跨领域可解释自然语言处理综述
Explainability in Practice: A Survey of Explainable NLP Across Various Domains
AI总结：
本综述针对实际部署的可解释NLP，覆盖7个应用领域，提出两级评估协议，探讨研究缺口并给出未来方向，为跨领域XNLP实践提供参考。
摘要：
自然语言处理（NLP）现已嵌入医疗、金融、客户关系管理等关键领域，GPT-4o、Gemini、BERT等模型正越来越多地为决策提供支撑。这些模型的黑箱特性催生了对透明度的迫切需求。本综述针对实际部署中的可解释NLP（XNLP）展开研究，覆盖医学、金融、系统评价、客户关系管理、聊天机器人、社会与行为科学、人力资源共7个应用领域。针对每个领域，我们探究该场景需要何种类型的解释、采用哪些方法以及如何对其进行评估。随后通过结构化跨领域综合分析对比各领域需求的差异，从范围、忠实性证据、计算成本三个维度对主要解释方法家族进行比较。我们还提出了一种两级评估协议，将共享的技术核心指标与解读这些指标所需的领域特定验证层相分离。本综述还探讨了XNLP文献中仍未充分覆盖的领域，包括实际适用性、保真度与忠实性之间的差距，以及人类判断在解释评估中的作用。最后给出了未来研究方向，其中包括个性化解释、人在回路评估，以及大语言模型的机制可解释性。
英文摘要：
Natural Language Processing (NLP) is now embedded in critical sectors including healthcare, finance, and customer relationship management, where models such as GPT-4o, Gemini, and BERT increasingly inform decisions. The black-box nature of these models has created an urgent need for transparency. This review examines explainable NLP (XNLP) as it is actually deployed, working through seven application domains: medicine, finance, systematic reviews, customer relationship management, chatbots, social and behavioral science, and human resources. For each domain, we ask what kind of explanation the setting needs, which methods are used there, and how they are evaluated. A structured cross-domain synthesis then contrasts how those requirements diverge. We compare the main explanation method families on scope, evidence of faithfulness, and computational cost. We also propose a two-tier evaluation protocol that separates a shared technical core of metrics from the domain-specific validation layer through which those metrics have to be read. The review also addresses areas that remain underrepresented in the XNLP literature, including real-world applicability, the gap between fidelity and faithfulness, and the role of human judgment in assessing explanations. It closes with research directions, among them personalized explanations, human-in-the-loop evaluation, and mechanistic interpretability for large language models.
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。
