用AI从航空报告中生成可追溯的安全隐患场景，辅助飞行系统安全分析。
Traceable LLM-Generated Hazard Scenarios for Operational Safety Analysis of Aviation Systems Using ASRS Reports
- 基于ASRS报告生成结构化假设与连贯事件叙述。
- 每条场景附真实历史共现概率评分和相似报告溯源。
- 结合进化逆向推理提升生成准确性，适合安全研究者使用。
航空系统运行中的操作性危险分析需综合考虑天气、空管行动、空域限制、飞机操作及人为因素的交互作用，区别于飞机系统层面的功能性危害评估。本文提出一种AI辅助方法，从美国宇航局航空安全报告系统（ASRS）中生成候选安全隐患场景。针对特定不良结果，该方法生成包含分类因素的结构化假设，并配套描述操作事件序列的叙事性场景。每个场景均附有基于历史共现证据的合理性评分，并可追溯至最相似的预留ASRS报告。进一步提出混合变体，通过进化逆向推理生成结构化假设，再用于引导叙事生成，从而提高正确性并降低变异。我们评估了多种大语言模型在零样本与少样本提示下的表现，以及可选微调的影响，衡量提示策略与模型选择对生成结构与叙事有效性及真实性的作用。
原文摘要 · Abstract (English)
Operational hazard analysis of aviation system operations must consider interactions among weather, ATC actions, airspace constraints, aircraft operations, and human factors - distinct from the functional hazard assessment applied at the aircraft-system level. We present an AI-assisted approach that generates candidate hazard scenarios from NASA's Aviation Safety Reporting System (ASRS). Given a target adverse outcome, it produces a structured hypothesis as categorical factors and a narrative scenario describing an operational event sequence consistent with the structure. Each scenario includes by a plausibility score from historical co-occurrence evidence and traceability to the most similar held-out ASRS reports. We then propose a hybrid variant, conditioning narrative generation on a structured hypothesis produced via evolutionary abduction, improving correctness and reducing variability. We evaluate multiple large language models, zero-shot versus few-shot prompting, and optional fine-tuning, measuring how prompting and model choice affect the validity and realism of the generated structures and narratives.
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。