Comhis at SemEval-2026 Task 4: Embedding-Space Adaptation and LLM-Assisted Inference for Narrative Similarity
Year: 2026
Type: conference-paper
Abstract: We present a two-stage system for the SemEval Narrative Similarity task that separates representation learning from comparative decision making.In Track B, we adapt a frozen largescale embedding model using a lightweight projection layer trained with a triplet objective and hard example mining, producing a task-specific similarity space.In Track A, similarity scores derived from the adapted embedding space are incorporated into a large language model, which performs the final binary decision.On the official test set, our system achieves 0.68 accuracy on Track A and 0.66 on Track B, clearly outperforming the provided baselines and ranking 20th out of 44 teams on Track A and 10th out of 27 teams on Track B. These results demonstrate that lightweight embedding adaptation, combined with LLM-based reasoning, provides an effective approach for modeling high-level narrative similarity.
Authors: Ke Shu, Eetu Mäkelä, Mikko Tolonen
Institution: University of Helsinki
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Awards: G1299453833, G6538956438
OpenAlex ID: W7166834492