From "Thinking" to "Justifying": Aligning High-Stakes Explainability with Professional Communication Standards
This addresses the need for trustworthy AI explanations in high-stakes domains, though it is incremental by adapting existing communication standards.
The paper tackles the problem of unreliable explanations in high-stakes XAI by proposing 'Result -> Justify', which presents conclusions before structured justifications, achieving 83.9% accuracy (+5.3 over Chain-of-Thought).
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.