GLaRef@CRAC2025: Should we transform coreference resolution into a text generation task?

Olga Seminck, Antoine Bourgois, Yoann Dupont, Mathieu Dehouck, Marine Delaborde


Abstract
We present the submissions of our team to the Unconstrained and LLM tracks of the Computational Models of Reference, Anaphora and Coreference (CRAC2025) shared task, where we ended respectively in the fifth and the first place, but nevertheless with similar scores: average CoNLL-F1 scores of 61.57 and 62.96 on the test set, but with very large differences in computational cost. Indeed, the classical pair-wise resolution system submitted to the Unconstrained track obtained similar performance but with less than 10% of the computational cost. Reflecting on this fact, we point out problems that we ran into using generative AI to perform coreference resolution. We explain how the framework of text generation stands in the way of a reliable text-global coreference representation. Nonetheless, we realize there are many potential improvements of our LLM-system; we discuss them at the end of this article.
Anthology ID:
2025.crac-1.10
Volume:
Proceedings of the Eighth Workshop on Computational Models of Reference, Anaphora and Coreference
Month:
November
Year:
2025
Address:
Suzhou, China
Editors:
Maciej Ogrodniczuk, Michal Novak, Massimo Poesio, Sameer Pradhan, Vincent Ng
Venue:
CRAC
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
119–129
Language:
URL:
https://aclanthology.org/2025.crac-1.10/
DOI:
Bibkey:
Cite (ACL):
Olga Seminck, Antoine Bourgois, Yoann Dupont, Mathieu Dehouck, and Marine Delaborde. 2025. GLaRef@CRAC2025: Should we transform coreference resolution into a text generation task?. In Proceedings of the Eighth Workshop on Computational Models of Reference, Anaphora and Coreference, pages 119–129, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
GLaRef@CRAC2025: Should we transform coreference resolution into a text generation task? (Seminck et al., CRAC 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.crac-1.10.pdf