FactUEP at SemEval-2026 Task 4: Structured Narrative Similarity Scoring with Aspect Decomposition and Weak-Signal Gating
Year: 2026
Type: conference-paper
Abstract: This paper presents approach to narrative similarity prediction for SemEval-2026 Task 4 Track A. We introduce an LLM-based system that operationalizes the three core dimensions-Abstract Theme, Course of Action, and Outcomes-via schema-constrained prompting to enforce structured outputs and alignment with the annotation protocol.The system proceeds in three stages: structured aspect decomposition and scoring, weak-signal gating for low-confidence cases, and a targeted LLM-based tiebreak.The final model achieved near-human performance and ranked second on the Track A leaderboard.
Author: Marcin Sawinski
Institution: Poznań University of Economics and Business
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7166817144