让AI先说结论再解释，提升高风险场景下的可信度
From "Thinking" to "Justifying": Aligning High-Stakes Explainability with Professional Communication Standards
- 先输出结论再结构化解释，符合专业沟通规范
- 新框架在四任务中准确率达83.9%，比传统方法高5.3%
- 适合医疗、司法等需可验证决策的领域使用
高风险领域中的可解释AI应帮助利益相关者信任并验证系统输出。然而，链式思维（CoT）方法在得出结论前进行推理，逻辑漏洞或幻觉可能导致结论与理由不一致。为此，我们提出“结果→论证”范式，要求模型先给出结论，再提供结构化解释。引入结构化可解释性框架（SEF），通过六项指标（如结构化、依据性）实现专业沟通惯例（如CREAC、BLUF）的可操作化。在三个领域四个任务上的实验表明，所有六项指标均与正确性显著相关（r=0.20–0.42；p<0.001），SEF达到83.9%准确率，较CoT提升5.3%。结果表明，结构化论证可增强可验证性，并可能提高可靠性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。