CorefUD

Fifth Shared Task on Multilingual Coreference Resolution: Long-Range Entities and LLM Participation

The fifth CODI-CRAC shared task on multilingual coreference resolution expanded its scope with five new datasets and two additional languages, leveraging CorefUD 1.4 covering 27 datasets across 19 languages. The 2026 edition emphasized long-range coreference chains spanning many words and sentences. Ten systems participated, including four LLM-based approaches; traditional systems still led but LLMs showed notable potential, suggesting competitive parity may be near.