Triadic Fusion of Cognitive, Functional, and Causal Dimensions for Explainable LLMs: The TAXAL Framework
This work addresses the need for trustworthy and context-sensitive explanations in agentic LLMs for high-risk applications, though it appears incremental as it synthesizes existing methods into a unified framework.
The paper tackles the problem of opacity and bias in LLMs used in high-risk domains by introducing TAXAL, a triadic fusion framework that unites cognitive, functional, and causal dimensions for explainability, demonstrating its applicability through case studies in law, education, healthcare, and public services.
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.