From "Thinking" to "Justifying": Aligning High-Stakes Explainability with Professional Communication Standards

TL;DR

This paper introduces a structured explainability framework for high-stakes AI that aligns with professional communication standards, improving trustworthiness and correctness of AI explanations.

Contribution

It proposes the 'Result -> Justify' approach and SEF framework, integrating professional conventions into AI explanations to enhance verifiability and reliability.

Findings

All six metrics correlate with correctness (r=0.20-0.42; p<0.001)

SEF achieves 83.9% accuracy, outperforming Chain-of-Thought by 5.3%

Structured justification improves verifiability and potentially reliability.

Abstract

Explainable AI (XAI) in high-stakes domains should help stakeholders trust and verify system outputs. Yet Chain-of-Thought methods reason before concluding, and logical gaps or hallucinations can yield conclusions that do not reliably align with their rationale. Thus, we propose "Result -> Justify", which constrains the output communication to present a conclusion before its structured justification. We introduce SEF (Structured Explainability Framework), operationalizing professional conventions (e.g., CREAC, BLUF) via six metrics for structure and grounding. Experiments across four tasks in three domains validate this approach: all six metrics correlate with correctness (r=0.20-0.42; p<0.001), and SEF achieves 83.9% accuracy (+5.3 over CoT). These results suggest structured justification can improve verifiability and may also improve reliability.