Can Large Language Models Explain Flight Safety Events? A Prior-Guided Semantic LLM-based Approach

• URL: http://arxiv.org/abs/2608.18017v1
• Date: Tue, 18 Aug 2026 17:11:40 GMT
• Title: Can Large Language Models Explain Flight Safety Events? A Prior-Guided Semantic LLM-based Approach
• Abstract summary: We propose FlightLLM, a prior-guided semantic LLM-based approach for interpretable flight safety analysis.<n>We first perform feature engineering to address modal inconsistency, combining statistical descriptors with physically meaningful flight indicators.<n>This representation is processed by a Semantic Discretization module, which converts abstract numerical patterns into qualitative descriptions.
• Score: 14.220005377497259
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Improving flight safety with flight data requires not only accurate detection of risk events, but more importantly, clear interpretation of their underlying causes at the level of pilot control behavior. Existing explainable AI techniques, such as feature importance maps, often require considerable domain knowledge to translate them into operationally meaningful explanations. Large Language Models (LLMs), which excel at language reasoning, bring a promising solution to this issue. However, applying LLMs in this domain presents key challenges such as modal inconsistency, limited classification ability, scarcity of task-specific data for fine-tuning, and lack of domain knowledge. To overcome these challenges, we propose FlightLLM, a prior-guided semantic LLM-based approach for interpretable flight safety analysis. Specifically, we first perform feature engineering to address modal inconsistency, combining statistical descriptors with physically meaningful flight indicators. This representation is further processed by a Semantic Discretization module, which converts abstract numerical patterns into qualitative descriptions that are more compatible with language reasoning. In addition, since LLMs are not inherently strong classifiers, CatBoost is incorporated as a statistical expert, and its prediction results are injected into the prompt as prior guidance. A contrastive few-shot learning strategy is further adopted to compensate for limited data. Finally, we design structured prompts to embed aviation-specific knowledge into the inference process. Using hard landing, a representative risk event with complex causal mechanisms, as an anchor point, we evaluate FlightLLM on a dataset of 704 real-world A320 flight samples. Experimental results show that the proposed approach achieves competitive classification performance while generating direct and reasonable explanations for event causes.

Related papers

• Inference-Time Steering for Cross-Lingual Factual Consistency in LLMs [51.56484100374058]
  Large Language Models (LLMs) demonstrate remarkable multilingual fluency, but their internal knowledge representations remain disproportionately biased toward high-resource languages.<n>We investigate whether these biases can be mitigated at inference time, forcing an English-prompted model to answer as if it were queried in target languages.<n>Experiments on Gemma 3 12B Instruct reveal persona prompting to be the strongest overall intervention, balancing efficacy, safety, and out-of-domain generalization.
  arXiv  Detail & Related papers  (2026-07-21T16:15:05Z)
• SCOPE: A Lightweight-training LLM Framework for Air Traffic Control Readback Monitoring [8.082279149607116]
  Air Traffic Control (ATC) voice instructions are a primary safeguard against miscommunication in air transportation.<n>Readback anomalies remain implicated in approximately 80% of aviation incidents.<n>Traditional rule-based and machine learning approaches struggle to generalize across the highly variable and evolving phraseology of ATC communications.<n>We propose a novel lightweight-training LLM framework that advances both the efficiency and accuracy of machine-based ATC readback monitoring.
  arXiv  Detail & Related papers  (2026-05-28T07:56:24Z)
• Knots: A Large-Scale Multi-Agent Enhanced Expert-Annotated Dataset and LLM Prompt Optimization for NOTAM Semantic Parsing [15.869090373058803]
  Notice to Air Missions (NOTAMs) serve as a critical channel for disseminating key flight safety information.<n>Their complex linguistic structures and implicit reasoning pose significant challenges for automated parsing.<n>We propose NOTAM semantic parsing, a task emphasizing semantic inference and the integration of aviation domain knowledge.
  arXiv  Detail & Related papers  (2025-11-16T14:52:24Z)
• Domain-Adapted Pre-trained Language Models for Implicit Information Extraction in Crash Narratives [6.91741018994547]
  We study whether compact open-source language models can support reasoning-intensive extraction from crash narratives.<n>We apply fine-tuning techniques to inject task-specific knowledge to LLMs with Low-Rank Adaption (LoRA) and BERT.<n>Further analysis reveals that the fine-tuned PLMs can capture richer narrative details and even correct some mislabeled annotations in the dataset.
  arXiv  Detail & Related papers  (2025-10-10T14:45:07Z)
• MARBLE: A Multi-Agent Rule-Based LLM Reasoning Engine for Accident Severity Prediction [1.3102025155414727]
  Accident severity prediction plays a critical role in transportation safety systems.<n>Existing methods often rely on monolithic models or black box prompting.<n>We propose a multiagent rule based LLM engine that decomposes the severity prediction task across a team of specialized reasoning agents.
  arXiv  Detail & Related papers  (2025-07-07T11:27:49Z)
• Do We Really Need Curated Malicious Data for Safety Alignment in Multi-modal Large Language Models? [83.53005932513155]
  Multi-modal large language models (MLLMs) have made significant progress, yet their safety alignment remains limited.<n>We propose finetuning MLLMs on a small set of benign instruct-following data with responses replaced by simple, clear rejection sentences.
  arXiv  Detail & Related papers  (2025-04-14T09:03:51Z)
• From Objects to Events: Unlocking Complex Visual Understanding in Object Detectors via LLM-guided Symbolic Reasoning [71.41062111470414]
  Current object detectors excel at entity localization and classification, yet exhibit inherent limitations in event recognition capabilities.<n>We present a novel framework that expands the capability of standard object detectors beyond mere object recognition to complex event understanding.<n>Our key innovation lies in bridging the semantic gap between object detection and event understanding without requiring expensive task-specific training.
  arXiv  Detail & Related papers  (2025-02-09T10:30:54Z)
• Large Language Models for Single-Step and Multi-Step Flight Trajectory Prediction [5.666505394825739]
  This study pioneers the use of large language models (LLMs) for flight trajectory prediction by reframing it as a language modeling problem.<n>Specifically, We features extract the aircraft's status and from ADS-B flight data to construct a prompt-based dataset.<n>The dataset is then employed to finetune LLMs, enabling them to learn complextemporal patterns for accurate predictions.
  arXiv  Detail & Related papers  (2025-01-29T07:35:56Z)
• Context is Key: A Benchmark for Forecasting with Essential Textual Information [87.3175915185287]
  "Context is Key" (CiK) is a forecasting benchmark that pairs numerical data with diverse types of carefully crafted textual context.<n>We evaluate a range of approaches, including statistical models, time series foundation models, and LLM-based forecasters.<n>We propose a simple yet effective LLM prompting method that outperforms all other tested methods on our benchmark.
  arXiv  Detail & Related papers  (2024-10-24T17:56:08Z)
• Learning Traffic Crashes as Language: Datasets, Benchmarks, and What-if Causal Analyses [76.59021017301127]
  We propose a large-scale traffic crash language dataset, named CrashEvent, summarizing 19,340 real-world crash reports. We further formulate the crash event feature learning as a novel text reasoning problem and further fine-tune various large language models (LLMs) to predict detailed accident outcomes. Our experiments results show that our LLM-based approach not only predicts the severity of accidents but also classifies different types of accidents and predicts injury outcomes.
  arXiv  Detail & Related papers  (2024-06-16T03:10:16Z)
• Unveiling the Misuse Potential of Base Large Language Models via In-Context Learning [61.2224355547598]
  Open-sourcing of large language models (LLMs) accelerates application development, innovation, and scientific progress. Our investigation exposes a critical oversight in this belief. By deploying carefully designed demonstrations, our research demonstrates that base LLMs could effectively interpret and execute malicious instructions.
  arXiv  Detail & Related papers  (2024-04-16T13:22:54Z)
• GroundCocoa: A Benchmark for Evaluating Compositional & Conditional Reasoning in Language Models [14.108788704400643]
  GroundCocoa is a lexically diverse benchmark connecting these reasoning skills to the real-world problem of flight booking.<n>Our task involves aligning detailed user preferences with available flight options presented in a multiple-choice format.<n>Results indicate a significant disparity in performance among current state-of-the-art LLMs with even the best performing model, GPT-4 Turbo, not exceeding 67% accuracy despite advanced prompting techniques.
  arXiv  Detail & Related papers  (2024-04-05T17:36:26Z)
• Efficient Prompt Tuning of Large Vision-Language Model for Fine-Grained Ship Classification [59.99976102069976]
  Fine-grained ship classification in remote sensing (RS-FGSC) poses a significant challenge due to the high similarity between classes and the limited availability of labeled data.<n>Recent advancements in large pre-trained Vision-Language Models (VLMs) have demonstrated impressive capabilities in few-shot or zero-shot learning.<n>This study delves into harnessing the potential of VLMs to enhance classification accuracy for unseen ship categories.
  arXiv  Detail & Related papers  (2024-03-13T05:48:58Z)

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.