面向可解释大语言模型的认知、功能与因果维度三元融合：TAXAL框架
Triadic Fusion of Cognitive, Functional, and Causal Dimensions for Explainable LLMs: The TAXAL Framework
AI总结：
针对传统可解释性方法无法捕捉智能体式LLM推理等深层问题，研究提出融合认知、功能、因果三维的TAXAL框架，整合现有方法并通过多领域案例验证，推动可解释性成为技术与社会技术实践。
摘要：
大语言模型（LLM）正越来越多地被部署于高风险领域，而这些领域中模型的不透明性、偏见与不稳定性会削弱信任与问责性。聚焦于表层输出的传统可解释性方法，无法捕捉智能体式LLM的推理路径、规划逻辑与系统性影响。\n我们提出TAXAL（Triadic Alignment for eXplainability in Agentic LLMs，智能体式大语言模型可解释性三元对齐框架），这是一个融合了三个互补维度的三元框架：认知维度（用户理解）、功能维度（实际效用）与因果维度（忠实推理）。TAXAL为在多元社会技术场景中设计、评估与部署解释方案提供了统一的、角色敏感的基础。\n我们的分析综合了现有各类方法，从事后归因、对话式界面到感知解释的提示工程，并将它们纳入TAXAL三元融合模型的框架下。我们进一步通过法律、教育、医疗保健与公共服务领域的案例研究验证了其适用性，展示了解释策略如何适配制度约束与利益相关者角色。\n通过将概念清晰性与设计模式、部署路径相结合，TAXAL推动可解释性成为一项技术与社会技术实践，为智能体AI时代中可信且适配场景的LLM应用提供支持。
英文摘要：
Large Language Models (LLMs) are increasingly being deployed in high-risk domains where opacity, bias, and instability undermine trust and accountability. Traditional explainability methods, focused on surface outputs, do not capture the reasoning pathways, planning logic, and systemic impacts of agentic LLMs. We introduce TAXAL (Triadic Alignment for eXplainability in Agentic LLMs), a triadic fusion framework that unites three complementary dimensions: cognitive (user understanding), functional (practical utility), and causal (faithful reasoning). TAXAL provides a unified, role-sensitive foundation for designing, evaluating, and deploying explanations in diverse sociotechnical settings. Our analysis synthesizes existing methods, ranging from post-hoc attribution and dialogic interfaces to explanation-aware prompting, and situates them within the TAXAL triadic fusion model. We further demonstrate its applicability through case studies in law, education, healthcare, and public services, showing how explanation strategies adapt to institutional constraints and stakeholder roles. By combining conceptual clarity with design patterns and deployment pathways, TAXAL advances explainability as a technical and sociotechnical practice, supporting trustworthy and context-sensitive LLM applications in the era of agentic AI.
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。
