Narrative Nexus at SemEval-2026 Task 4: Modeling Narrative Similarity via Instruction-Based Fine-Tuning and Synthetic Data Augmentation
TL;DR
This paper addresses SemEval-2026 Task 4 Track A: Narrative Story Similarity by reformulating it as an instruction-following generation problem, employing parameter-efficient fine-tuning via LoRA to adapt pretrained large language models for triplet-based narrative comparison and incorporating synthetic triplet samples generated by a large language model for data augmentation.
Abstract
Narrative similarity assessment requires models to reason beyond surface-level lexical overlap and capture higher-level plot structures and thematic relationships. In this paper, we address SemEval-2026 Task 4 Track A: Narrative Story Similarity by reformulating it as an instruction-following generation problem. We employ parameter-efficient fine-tuning via LoRA to adapt pretrained large language models for triplet-based narrative comparison. To overcome the limitations imposed by the scarcity of human-annotated data, we further incorporate organizer-provided synthetic triplet samples generated by a large language model for data augmentation. Experimental results demonstrate that our fine-tuned Qwen2.5-7B model achieves slightly better performance than the zero-shot GPT-4o-mini base-line. These findings underscore the effectiveness of task-specific adaptation combined with synthetic data augmentation for narrative similarity modeling.