{"ID":2867761,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.17858","arxiv_id":"2509.17858","title":"CorPipe at CRAC 2025: Evaluating Multilingual Encoders for Multilingual Coreference Resolution","abstract":"We present CorPipe 25, the winning entry to the CRAC 2025 Shared Task on Multilingual Coreference Resolution. This fourth iteration of the shared task introduces a new LLM track alongside the original unconstrained track, features reduced development and test sets to lower computational requirements, and includes additional datasets. CorPipe 25 represents a complete reimplementation of our previous systems, migrating from TensorFlow to PyTorch. Our system significantly outperforms all other submissions in both the LLM and unconstrained tracks by a substantial margin of 8 percentage points. The source code and trained models are publicly available at https://github.com/ufal/crac2025-corpipe.","short_abstract":"We present CorPipe 25, the winning entry to the CRAC 2025 Shared Task on Multilingual Coreference Resolution. This fourth iteration of the shared task introduces a new LLM track alongside the original unconstrained track, features reduced development and test sets to lower computational requirements, and includes addit...","url_abs":"https://arxiv.org/abs/2509.17858","url_pdf":"https://arxiv.org/pdf/2509.17858v2","authors":"[\"Milan Straka\"]","published":"2025-09-22T14:51:37Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Large Language Model\"]","has_code":false,"code_links":[{"ID":609509,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2867761,"paper_url":"https://arxiv.org/abs/2509.17858","paper_title":"CorPipe at CRAC 2025: Evaluating Multilingual Encoders for Multilingual Coreference Resolution","repo_url":"https://github.com/ufal/crac2025-corpipe","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}