27th EAAAI (EANN) 2026, 16 - 19 July 2026, Chania, Crete, Greece

Constructivist Summarization Meets Clustering: A Hybrid LLM-Based Framework for Aviation Incident Knowledge Extraction

Hatoum Carl, Combes Catherine, Fresse Virginie, Gravier Christophe, Orzalesi Mathieu

Abstract:

  We propose a hybrid framework for knowledge extraction from large text corpora that combines aspect-conditioned LLM summarization with clustering-based topic modeling. The approach selects the most semantically stable prompting strategy via entropy minimization, generates aspect-focused summaries, and applies QA-based filtering before clustering. Applied to aviation incident reports, decomposed chain-of-thought prompting substantially reduces semantic instability compared to zero-shot generation while preserving macro-level thematic structure. The resulting topics are more causally oriented, improving interpretability while maintaining structural fidelity to the underlying corpus.  

*** Title, author list and abstract as submitted during Camera-Ready version delivery. Small changes that may have occurred during processing by Springer may not appear in this window.