Few-Shot Coreference Resolution with Semantic Difficulty Metrics and In-Context Learning
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F26%3AR7ZNZRIS" target="_blank" >RIV/00216208:11320/26:R7ZNZRIS - isvavai.cz</a>
Result on the web
<a href="https://aclanthology.org/2025.crac-1.13/" target="_blank" >https://aclanthology.org/2025.crac-1.13/</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.18653/v1/2025.crac-1" target="_blank" >10.18653/v1/2025.crac-1</a>
Alternative languages
Result language
angličtina
Original language name
Few-Shot Coreference Resolution with Semantic Difficulty Metrics and In-Context Learning
Original language description
This paper presents our submission to the CRAC 2025 Shared Task on Multilingual Coreference Resolution in the LLM track. We propose a prompt-based few-shot coreference resolution system where the final inference is performed by Grok-3 using in-context learning. The core of our methodology is a difficulty- aware sample selection pipeline that leverages Gemini Flash 2.0 to compute semantic diffi- culty metrics, including mention dissimilarity and pronoun ambiguity. By identifying and selecting the most challenging training sam- ples for each language, we construct highly informative prompts to guide Grok-3 in predict- ing coreference chains and reconstructing zero anaphora. Our approach secured 3rd place in the CRAC 2025 shared task.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
—
Continuities
—
Others
Publication year
2025
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Proceedings of the Eighth Workshop on Computational Models of Reference, Anaphora and Coreference
ISBN
979-8-89176-342-5
ISSN
—
e-ISSN
—
Number of pages
5
Pages from-to
149-153
Publisher name
—
Place of publication
—
Event location
Suzhou, China
Event date
Jan 1, 2026
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—