Findings of the Fifth Shared Task on Multilingual Coreference Resolution: Expanding Datasets for Long-Range Entities

TL;DR

This paper reports on the fifth multilingual coreference resolution shared task, emphasizing long-range entities, expanding datasets and languages, and evaluating traditional and LLM-based systems' performance.

Contribution

It introduces new datasets and languages for the shared task, highlights the focus on long-range entities, and compares traditional systems with emerging LLM approaches.

Findings

Traditional systems still lead in performance.

LLMs show promising potential for future improvements.

Expanded datasets and languages enhance the task's scope.

Abstract

This paper describes the fifth edition of the Shared Task on Multilingual Coreference Resolution, held in conjunction with the CODI-CRAC 2026 workshop. Building on previous iterations, the task required participants to develop systems capable of mention identification and identity-based coreference clustering. The 2026 edition specifically emphasizes long-range entities, defined as coreferential chains spanning significant distances, across many words and sentences. The task expanded its linguistic scope by incorporating five new datasets and two additional languages. These additions leverage version 1.4 of CorefUD, a harmonized multilingual collection comprising 27 datasets in 19 languages. In total, ten systems participated, including four LLM-based approaches (three fine-tuned models and one few-shot approach). While traditional systems still maintained their lead, LLMs demonstrated significant potential, suggesting they may soon challenge established approaches in future editions.