通过LLM驱动的标准流程提升人工智能可解释性
Increasing AI Explainability by LLM Driven Standard Processes
AI总结：
本文提出将LLM嵌入QOC、敏感性分析、博弈论等标准化决策流程，通过分层架构将不透明推理转化为可审计的决策轨迹，并在多个场景中验证其可重现人类级决策逻辑，为可解释AI辅助决策提供基础。
摘要：
本文介绍了一种通过将大语言模型（LLMs）嵌入标准化分析流程来提升人工智能（AI）系统可解释性的方法。传统的可解释人工智能（XAI）方法侧重于特征归因或事后解释，而本文提出的框架将LLMs集成到明确界定的决策模型中，例如问题-选项-标准（QOC）、敏感性分析、博弈论和风险管理。通过将LLM推理置于这些形式化结构之中，该方法将不透明的推理过程转化为透明且可审计的决策轨迹。本文提出了一种分层架构，将LLM的推理空间与其上方的可解释流程空间分离开来。实证评估表明，该系统能够在去中心化治理、系统分析和战略推理等场景中重现人类水平的决策逻辑。结果表明，LLM驱动的标准流程为可靠、可解释且可验证的AI辅助决策奠定了基础。
英文摘要：
This paper introduces an approach to increasing the explainability of artificial intelligence (AI) systems by embedding Large Language Models (LLMs) within standardized analytical processes. While traditional explainable AI (XAI) methods focus on feature attribution or post-hoc interpretation, the proposed framework integrates LLMs into defined decision models such as Question-Option-Criteria (QOC), Sensitivity Analysis, Game Theory, and Risk Management. By situating LLM reasoning within these formal structures, the approach transforms opaque inference into transparent and auditable decision traces. A layered architecture is presented that separates the reasoning space of the LLM from the explainable process space above it. Empirical evaluations show that the system can reproduce human-level decision logic in decentralized governance, systems analysis, and strategic reasoning contexts. The results suggest that LLM-driven standard processes provide a foundation for reliable, interpretable, and verifiable AI-supported decision making.
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。
