Year: 2026
Type: conference-paper
Abstract: In this work, we applied two different systems to the SemEval 2026 Shared Task 12 (SemEval-2026 Task 12 Organizers, 2026), which explores abductive event reasoning.Specifically, this task involves determining the cause of an event from a list of candidate causes.Instances are accompanied with documents that can provide applicable knowledge for the target event.Both of our systems involve prompting LLMs and our best performing system leverages retrieval-augmented generation.Our best performing system achieved a score of 84% and ranked 40th out of 221 total submissions.
Authors: Caelen Mattie, Patrick Bowen, Milton King
Institution: St. Francis Xavier University
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7166856359