Traceable LLM-Generated Hazard Scenarios for Operational Safety Analysis of Aviation Systems Using ASRS Reports

• URL: http://arxiv.org/abs/2608.04697v1
• Date: Wed, 05 Aug 2026 11:07:17 GMT
• Title: Traceable LLM-Generated Hazard Scenarios for Operational Safety Analysis of Aviation Systems Using ASRS Reports
• Abstract summary: We present an AI-assisted approach that generates candidate hazard scenarios from NASA's Aviation Safety Reporting System (ASRS)<n>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.<n>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.
• Score: 8.323726651684021
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Uncertainty-Aware Conflict Detection Against Operator-Conditioned Weather Hazards [0.6299766708197883]
  AAM environments require robust methods for predicting aircraft state uncertainty and detecting potential conflicts with dynamic airspace hazards.<n>This paper presents a novel framework for uncertainty-conditioned trajectory prediction combined with polyhedra hazard representation for pre-flight conflict detection.
  arXiv  Detail & Related papers  (2026-09-10T18:18:42Z)
• Bridging Predictive Uncertainty and Safe Action: Sample-Conditioned Differentiable Planning for Autonomous Driving [46.91409391705346]
  Complex, dynamic, and interactive driving environments pose significant challenges for autonomous driving.<n>A fundamental bottleneck in current systems is the disconnect between highly expressive uncertainty modeling and interpretable, safe motion planning.<n>We propose a novel sample-conditioned differentiable planning framework that bridges this gap by explicitly incorporating diffusion-generated future trajectories into the optimization process.
  arXiv  Detail & Related papers  (2026-06-02T08:10:02Z)
• Emergent Strategic Reasoning Risks in AI: A Taxonomy-Driven Evaluation Framework [63.74295981594549]
  Large language models (LLMs) engage in behaviors that serve their own objectives.<n>These include, but are not limited to, deception (intentionally misleading users or evaluators), evaluation gaming (strategically manipulating performance during safety testing), and reward hacking.<n>We introduce ESRRSim, a taxonomy-driven agentic framework for automated behavioral risk evaluation.
  arXiv  Detail & Related papers  (2026-04-23T23:44:01Z)
• Risk Is Not the Target: A Monotonic Framework for Evaluating Wildfire Operational Risk Signals [0.9099663022952497]
  evaluating wildfire risk systems using standard machine-learning metrics such as F1-score or IoU is fundamentally flawed.<n>This work proposes a novel monotonic evaluation framework that measures whether increases in a predicted risk score consistently correspond to increases in observed operational load.
  arXiv  Detail & Related papers  (2026-04-23T11:28:57Z)
• Taming Actor-Observer Asymmetry in Agents via Dialectical Alignment [59.536125286960186]
  Multi-agent frameworks assigning specialized roles are increasingly adopted to enable self-reflection and mutual auditing.<n>We find it simultaneously induces a human-like cognitive bias known as Actor-Observer Asymmetry.<n>ReTAS guides agents to synthesize conflicting viewpoints into an objective consensus.
  arXiv  Detail & Related papers  (2026-04-21T15:05:58Z)
• Fine-Tuning Large Language Models for Cooperative Tactical Deconfliction of Small Unmanned Aerial Systems [3.3091223236295213]
  Small Unmanned Aerial Systems (sUASs) in low-altitude airspaces have increased the need for reliable tactical deconfliction under safety-critical constraints.<n>This paper investigates Large Language Models (LLMs) as decision-makers in cooperative multi-agent tactical deconfliction using fine-tuning strategies.
  arXiv  Detail & Related papers  (2026-03-30T15:22:27Z)
• Dual-Stage LLM Framework for Scenario-Centric Semantic Interpretation in Driving Assistance [3.7098231493739764]
  This paper presents a scenario-centric framework for reproducible auditing of risk reasoning in urban driving contexts.<n>Findings highlight the importance of scenario-centric auditing and explicit ambiguity management when integrating LLM-based reasoning into safety-aligned driver assistance systems.
  arXiv  Detail & Related papers  (2026-03-29T06:20:08Z)
• Building a Foundational Guardrail for General Agentic Systems via Synthetic Data [76.18834864749606]
  LLM agents can plan multi-step tasks, intervening at the planning stage-before any action is executed-is often the safest way to prevent harm.<n>Existing guardrails mostly operate post-execution, which is difficult to scale and leaves little room for controllable supervision at the plan level.<n>We introduce AuraGen, a controllable engine that synthesizes benign trajectories, injects category-labeled risks with difficulty, and filters outputs via an automated reward model.
  arXiv  Detail & Related papers  (2025-10-10T18:42:32Z)
• SAFE-SIM: Safety-Critical Closed-Loop Traffic Simulation with Diffusion-Controllable Adversaries [94.84458417662407]
  We introduce SAFE-SIM, a controllable closed-loop safety-critical simulation framework. Our approach yields two distinct advantages: 1) generating realistic long-tail safety-critical scenarios that closely reflect real-world conditions, and 2) providing controllable adversarial behavior for more comprehensive and interactive evaluations. We validate our framework empirically using the nuScenes and nuPlan datasets across multiple planners, demonstrating improvements in both realism and controllability.
  arXiv  Detail & Related papers  (2023-12-31T04:14:43Z)
• Inferring Traffic Models in Terminal Airspace from Flight Tracks and Procedures [39.89295870460643]
  We propose a simple probabilistic model that can learn variability from procedural data and flight tracks collected from radar surveillance data.<n>We generate synthetic trajectories by sampling a series of deviations from the Gaussian mixture model and reconstructing the aircraft trajectory.<n>We demonstrate the proposed models on the arrival tracks and procedures of the John F. Kennedy International Airport.
  arXiv  Detail & Related papers  (2023-03-17T13:58:06Z)
• Generating and Characterizing Scenarios for Safety Testing of Autonomous Vehicles [86.9067793493874]
  We propose efficient mechanisms to characterize and generate testing scenarios using a state-of-the-art driving simulator. We use our method to characterize real driving data from the Next Generation Simulation (NGSIM) project. We rank the scenarios by defining metrics based on the complexity of avoiding accidents and provide insights into how the AV could have minimized the probability of incurring an accident.
  arXiv  Detail & Related papers  (2021-03-12T17:00:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.