Building Trust in the Skies: A Knowledge-Grounded LLM-based Framework for Aviation Safety
Anirudh Iyengar, Alisa Tiselska, Dumindu Samaraweera, Hong Liu
Why It Matters
What makes this one worth your time
This research is crucial for the aviation industry, where safety decisions must be accurate and verifiable, especially given the increasing reliance on AI technologies.
A novel framework enhances aviation safety by combining LLMs with Knowledge Graphs for reliable decision-making.
Summary
The paper proposes a framework that integrates Large Language Models with Knowledge Graphs to improve the reliability of aviation safety decision-making by addressing issues like hallucination and factual inaccuracies.
Key contributions
- Development of an end-to-end framework combining LLMs and Knowledge Graphs for aviation safety.
- Implementation of a dual-phase pipeline for dynamic knowledge graph construction.
- Demonstration of improved accuracy and traceability in safety analytics compared to LLM-only approaches.
Notable insights
- The dual-phase pipeline for constructing and updating the Aviation Safety Knowledge Graph is a clever approach to mitigate LLM limitations.
- The use of a Retrieval-Augmented Generation architecture to ground LLM outputs enhances the traceability of safety insights.
Possible limitations
- Not stated in the abstract.
Abstract
arXiv:2604.13101v1 Announce Type: cross Abstract: The integration of Large Language Models (LLMs) into aviation safety decision-making represents a significant technological advancement, yet their standalone application poses critical risks due to inherent limitations such as factual inaccuracies, hallucination, and lack of verifiability. These challenges undermine the reliability required for safety-critical environments where errors can have catastrophic consequences. To address these challenges, this paper proposes a novel, end-to-end framework that synergistically combines LLMs and Knowledge Graphs (KGs) to enhance the trustworthiness of safety analytics. The framework introduces a dual-phase pipeline: it first employs LLMs to automate the construction and dynamic updating of an Aviation Safety Knowledge Graph (ASKG) from multimodal sources. It then leverages this curated KG within a Retrieval-Augmented Generation (RAG) architecture to ground, validate, and explain LLM-generated responses. The implemented system demonstrates improved accuracy and traceability over LLM-only approaches, effectively supporting complex querying and mitigating hallucination. Results confirm the framework's capability to deliver context-aware, verifiable safety insights, addressing the stringent reliability requirements of the aviation industry. Future work will focus on enhancing relationship extraction and integrating hybrid retrieval mechanisms.