作者位次 #3/5ACL 2026Findings· Findings of ACL
From “Thinking” to “Justifying”: Aligning High-Stakes Explainability with Professional Communication Standards
Chen Qian · Yimeng Wang · Yu Chen · Lingfei Wu · Andreas Stathopoulos
摘要
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...