Lacuna Inc. at SemEval-2026 Task 4: Structurally Gated State-Space Models for Disentangling Narrative Similarity
For researchers in narrative understanding and computational semantics, this work introduces a novel method to address the bottleneck of modeling long-range causal dependencies without quadratic complexity, though results are presented qualitatively without concrete numbers.
The authors propose IVD-SSM, a hybrid state-space model with a Structurally Gated Alignment head for narrative similarity, achieving robust performance on SemEval-2026 Task 4 by disentangling structural invariants from lexical variants.
In this paper, we present the Invariant-Variant Disentangled State-Space Model (IVD-SSM), our submission to SemEval-2026 Task 4 on Narrative Story Similarity and Narrative Representation Learning. Evaluating narrative similarity is a profound computational challenge that requires models to look past concrete, superficial elements such as specific names, actors, objects, or settings to isolate and compare abstract patterns of causality and plot progression. To model these extended causal chains without the quadratic bottlenecks of standard Transformers, we leverage a hybrid State-Space Model (Jamba-1.5-Mini). Building upon this backbone, we introduce the Structurally Gated Alignment (SGA) head, a novel, differentiable algorithmic architecture. The SGA head operates on two scales: a heavily strided Macro-path maps the coarse structural skeleton of a story, which then acts as a gating mechanism to filter a full-resolution Micro-path, actively suppressing semantic noise and superficial keyword overlaps. Evaluated on both pairwise comparative judgments (Track A) and dense representation learning (Track B), our approach demonstrates that explicitly disentangling structural invariants from lexical variants provides a robust, principled framework for deep narrative understanding.