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

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F26%3AHK5PHB6V" target="_blank" >RIV/00216208:11320/26:HK5PHB6V - isvavai.cz</a>

Výsledek na webu

<a href="https://aclanthology.org/2025.crac-1.10/" target="_blank" >https://aclanthology.org/2025.crac-1.10/</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

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

Popis výsledku v původním jazyce

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.

Název v anglickém jazyce

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

Popis výsledku anglicky

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.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

—

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Proceedings of the Eighth Workshop on Computational Models of Reference, Anaphora and Coreference

ISBN

979-8-89176-342-5

ISSN

—

e-ISSN

—

Počet stran výsledku

11

Strana od-do

119-129

Název nakladatele

—

Místo vydání

—

Místo konání akce

Suzhou, China

Datum konání akce

1. 1. 2026

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—