PulseAugur
EN
LIVE 16:50:39

Gemma-3-27b model tops multilingual coreference resolution task

By PulseAugur Editorial · [2 sources] ·

Researchers achieved first place in the LLM track of the 2026 Computational Models of Reference, Anaphora and Coreference (CRAC 2026) shared task with a system that ranked third overall. Their approach, based on the Gemma-3-27b model, employed a two-stage adaptation strategy. This method proved effective across various languages and document complexities, achieving a 74.32 CoNLL F1 score. AI

IMPACT Advances in multilingual coreference resolution could improve the performance of downstream NLP tasks like summarization and question answering.

RANK_REASON The cluster describes the findings and winning system of a shared task focused on multilingual coreference resolution, including details about the model and its performance.

Read on arXiv cs.CL →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

Gemma-3-27b model tops multilingual coreference resolution task

How we ranked this

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Research
The cluster describes the findings and winning system of a shared task focused on multilingual coreference resolution, including details about the model and its performance.
Source corroboration
2 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics
paper, model release
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
141 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

Full methodology in our editorial standards.

COVERAGE [2]

  1. arXiv cs.CL TIER_1 English(EN) · Antoine Bourgois, Olga Seminck, Thierry Poibeau ·

    Closing the Gap at CRAC 2026: Two-Stage Adaptation for LLM-Based Multilingual Coreference Resolution

    arXiv:2605.16984v2 Announce Type: replace Abstract: We present our submission to the LLM track of the 2026 Computational Models of Reference, Anaphora and Coreference (CRAC 2026) shared task. With an average CoNLL F1 score of 74.32 on the official test set, our system ranked firs…

  2. arXiv cs.CL TIER_1 English(EN) · Daniel Zeman ·

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

    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 identit…

RELATED ENTITIES

RELATED TOPICS