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

arXiv: https://arxiv.org/abs/2605.16984 · HTML: https://mlsanity.com/paper/2605.16984/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 54 references that are in the map.
- First posted on arXiv 16 May 2026.

## Builds on (most cited first, 21 of 21)

- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [End-to-end Neural Coreference Resolution](https://mlsanity.com/paper/1707.07045/) (2017)
- [DocRED: A Large-Scale Document-Level Relation Extraction Dataset](https://mlsanity.com/paper/1906.06127/) (2019)
- [BERT for Coreference Resolution: Baselines and Analysis](https://mlsanity.com/paper/1908.09091/) (2019)
- [An Annotated Dataset of Coreference in English Literature](https://mlsanity.com/paper/1912.01140/) (2019)
- [Word-Level Coreference Resolution](https://mlsanity.com/paper/2109.04127/) (2021)
- [Coreference-Aware Dialogue Summarization](https://mlsanity.com/paper/2106.08556/) (2021)
- [Moving on from OntoNotes: Coreference Resolution Model Transfer](https://mlsanity.com/paper/2104.08457/) (2021)
- [Findings of the Shared Task on Multilingual Coreference Resolution](https://mlsanity.com/paper/2209.07841/) (2022)
- [Seq2seq is All You Need for Coreference Resolution](https://mlsanity.com/paper/2310.13774/) (2023)
- [Findings of the Third Shared Task on Multilingual Coreference Resolution](https://mlsanity.com/paper/2410.15949/) (2024)
- [Findings of the Fourth Shared Task on Multilingual Coreference Resolution: Can LLMs Dethrone Traditional Approaches?](https://mlsanity.com/paper/2509.17796/) (2025)
- [Seeing the Forest and the Trees: Detection and Cross-Document Coreference Resolution of Militarized Interstate Disputes](https://mlsanity.com/paper/2005.02966/) (2020)
- [Coreference Resolution for the Biomedical Domain: A Survey](https://mlsanity.com/paper/2109.12424/) (2021)
- [A Controlled Reevaluation of Coreference Resolution Models](https://mlsanity.com/paper/2404.00727/) (2024)
- [LegalCore: A Dataset for Event Coreference Resolution in Legal Documents](https://mlsanity.com/paper/2502.12509/) (2025)
- [The Elephant in the Coreference Room: Resolving Coreference in Full-Length French Fiction Works](https://mlsanity.com/paper/2510.15594/) (2025)
- [CorPipe at CRAC 2025: Evaluating Multilingual Encoders for Multilingual Coreference Resolution](https://mlsanity.com/paper/2509.17858/) (2025)
- [Context-Aware Machine Translation with Source Coreference Explanation](https://mlsanity.com/paper/2404.19505/) (2024)
- [Modeling the Construction of a Literary Archetype: The Case of the Detective Figure in French Literature](https://mlsanity.com/paper/2511.00627/) (2025)

## Abstract (arXiv)

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 first in the LLM track, and third overall. Our system is based on the Gemma-3-27b model, fine-tuned using a two-stage strategy with a multilingual base adapter followed by dataset-specific adapters. We represent mention spans by their headword using an XML-inspired format with local reindexing and annotate documents iteratively. These design choices proved effective across languages, document lengths, and annotation guidelines.