语言模型在航空管制中看似准确，实则存在安全风险盲区。
Beyond Semantic Accuracy: Consequence-Aware Evaluation for Safety-Critical Language Understanding
- 用后果感知评估框架检验模型真实安全性
- 8个模型在标准指标上表现良好，但安全评估结果差
- 适合评估高风险场景下的AI可靠性
语言模型能否在安全关键任务中被信任？在这些场景中，语义指标表现优秀并不意味着实际操作可靠：读错高度、遗漏执行条件或混淆呼号，虽在标准F1指标上得分较高，却可能带来严重后果。本文以空中交通管制（ATC）为场景，该领域对错误容忍度近乎为零，采用后果感知评估方法检验语义分数是否虚高。研究基于航空标准构建可控诊断基准，并整合来自三个国家40名空中交通管制员的反馈。评估8个模型后发现，存在系统性语义-安全差距：即使模型在常规指标上表现可靠，其真实安全性能仍被显著高估。风险感知微调可缩小但无法消除该差距，表明后果感知评估是部署前不可或缺的补充，必须与传统NLP指标并行使用。
原文摘要 · Abstract (English)
Can language models be trusted in safety- critical operations? In such settings, strong per- formance on semantic metrics does not guaran- tee operational reliability: a misread altitude, a dropped execution condition, or a confused call- sign may score well under standard F1 yet carry sharply asymmetric operational consequences. We study this problem in air traffic control (ATC), where controller-pilot communication demands near-zero error tolerance, and use consequence-aware evaluation to test whether semantic scores misstate operational reliabil- ity. The framework is instantiated in a con- trolled diagnostic ATC benchmark grounded in aviation standards and feedback from 40 air traffic controllers across three countries. Evaluating 8 models, we uncover a system- atic semantic-safety gap: conventional scores give substantially higher performance estimates than consequence-aware evaluation, even for models that appear reliable under standard met- rics. Risk-aware fine-tuning narrows but does not close this gap, showing that consequence- aware evaluation is a necessary complement to standard NLP metrics before any real safety- critical deployment claim
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。