NarSiL at SemEval-2026 Task 4: A Multi-Expert, Multi-Pathway System for Narrative Story Similarity
This work presents NarSiL 1, a system for SemEval-2026 Task 4 Track A on Narrative Story Similarity that employs a Mixture-of-Experts initial classifier that also leverages supermajority voting across three large language models, followed by a structured three-pathway fallback for ambiguous cases.