SemEval-2026 Task 12: Knowledge Graph with hyperbolic embedding in Abductive Event Reasoning
Year: 2026
Type: conference-paper
Abstract: this task introduces Abductive Event Reasoning (AER), a novel shared task, to investigate the ability of Large Language Models(LLMs) to reason about the causality of realworld events.More specifically, a data set consisting of different topics and choices is introduced, and we need to enable the model to select the best options for the given event.Three methods are separately introduced to explore the question, including the traditional natural language processing(NLP) method (DeBERTa), the enhanced knowledge graph(KG), and the KG embedded in hyperbolic space.Our implementation could be downloaded: https://github. com/MingkaiW/SemEval2026-task12
Authors: Mingkai Wang, Varun Ojha, Huizhi Liang
Institution: Newcastle University
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7166803169