Work

Team HITS at SemEval-2026 Task 4:Enhancing narrative text embedding model training with hard negatives generation and self-distillation

Year: 2026

Type: conference-paper

Abstract: Narrative text embedding is the basis for machines to understand and represent stories.However, it is challenging because it depends on similarities in theme, course of action, and outcomes.To target this challenge, we present a task-aligned system for SemEval-2026 Task 4 Track B. We first use Qwen2.5-32B-Instructmodel to generate hard negatives from three narrative dimensions.We then train a Qwen3-Embedding-8B model with a multi-negative contrastive objective and use a teacher model that has the same architecture as the training model.The model achieves the best result in the current training phase by introducing "soft label" via KL Divergence.

Source: International Workshop on Semantic Evaluation (SemEval)

DOI: 10.18653/v1/2026.semeval-1.338

Authors: Qian Zhou, Yi Fan, Wei Liu, Michael Strube

Institutions: Heidelberg University, Heidelberg Institute for Theoretical Studies

Language: English

Topic: Topic Modeling

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funder: Klaus Tschira Stiftung

OpenAlex ID: W7166807251