Findings of the Fourth Shared Task on Multilingual Coreference Resolution: Can LLMs Dethrone Traditional Approaches?
This work addresses coreference resolution for multilingual NLP applications, but it is incremental as it builds on previous shared tasks with minor innovations.
The paper presents results from the fourth Shared Task on Multilingual Coreference Resolution, where nine systems, including four LLM-based approaches, were evaluated on expanded datasets in 17 languages, finding that traditional systems still lead but LLMs show potential for future challenges.
The paper presents an overview of the fourth edition of the Shared Task on Multilingual Coreference Resolution, organized as part of the CODI-CRAC 2025 workshop. As in the previous editions, participants were challenged to develop systems that identify mentions and cluster them according to identity coreference. A key innovation of this year's task was the introduction of a dedicated Large Language Model (LLM) track, featuring a simplified plaintext format designed to be more suitable for LLMs than the original CoNLL-U representation. The task also expanded its coverage with three new datasets in two additional languages, using version 1.3 of CorefUD - a harmonized multilingual collection of 22 datasets in 17 languages. In total, nine systems participated, including four LLM-based approaches (two fine-tuned and two using few-shot adaptation). While traditional systems still kept the lead, LLMs showed clear potential, suggesting they may soon challenge established approaches in future editions.