# CorefInst: Leveraging LLMs for Multilingual Coreference Resolution

arXiv: https://arxiv.org/abs/2509.17505 · HTML: https://mlsanity.com/paper/2509.17505/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 43 references that are in the map.
- First posted on arXiv 22 Sep 2025.

## Builds on (most cited first, 23 of 23)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Multitask Prompted Training Enables Zero-Shot Task Generalization](https://mlsanity.com/paper/2110.08207/) (2021)
- [SpanBERT: Improving Pre-training by Representing and Predicting Spans](https://mlsanity.com/paper/1907.10529/) (2019)
- [DeepSeek LLM: Scaling Open-Source Language Models with Longtermism](https://mlsanity.com/paper/2401.02954/) (2024)
- [End-to-end Neural Coreference Resolution](https://mlsanity.com/paper/1707.07045/) (2017)
- [Higher-order Coreference Resolution with Coarse-to-fine Inference](https://mlsanity.com/paper/1804.05392/) (2018)
- [Coreference Resolution as Query-based Span Prediction](https://mlsanity.com/paper/1911.01746/) (2019)
- [Generative Pre-trained Transformer: A Comprehensive Review on Enabling Technologies, Potential Applications, Emerging Challenges, and Future Directions](https://mlsanity.com/paper/2305.10435/) (2023)
- [Improving Coreference Resolution by Learning Entity-Level Distributed Representations](https://mlsanity.com/paper/1606.01323/) (2016)
- [Autoregressive Structured Prediction with Language Models](https://mlsanity.com/paper/2210.14698/) (2022)
- [Coreference-Aware Dialogue Summarization](https://mlsanity.com/paper/2106.08556/) (2021)
- [Coreference Resolution through a seq2seq Transition-Based System](https://mlsanity.com/paper/2211.12142/) (2022)
- [deep-significance - Easy and Meaningful Statistical Significance Testing in the Age of Neural Networks](https://mlsanity.com/paper/2204.06815/) (2022)
- [Learning Global Features for Coreference Resolution](https://mlsanity.com/paper/1604.03035/) (2016)
- [CAW-coref: Conjunction-Aware Word-level Coreference Resolution](https://mlsanity.com/paper/2310.06165/) (2023)
- [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)
- [What GPT Knows About Who is Who](https://mlsanity.com/paper/2205.07407/) (2022)
- ['UFAL CorPipe at CRAC 2023: Larger Context Improves Multilingual Coreference Resolution](https://mlsanity.com/paper/2311.14391/) (2023)
- [CorPipe at CRAC 2024: Predicting Zero Mentions from Raw Text](https://mlsanity.com/paper/2410.02756/) (2024)

## Abstract (arXiv)

Coreference Resolution (CR) is a crucial yet challenging task in natural language understanding, often constrained by task-specific architectures and encoder-based language models that demand extensive training and lack adaptability. This study introduces the first multilingual CR methodology which leverages decoder-only LLMs to handle both overt and zero mentions. The article explores how to model the CR task for LLMs via five different instruction sets using a controlled inference method. The approach is evaluated across three LLMs; Llama 3.1, Gemma 2, and Mistral 0.3. The results indicate that LLMs, when instruction-tuned with a suitable instruction set, can surpass state-of-the-art task-specific architectures. Specifically, our best model, a fully fine-tuned Llama 3.1 for multilingual CR, outperforms the leading multilingual CR model (i.e., Corpipe 24 single stage variant) by 2 pp on average across all languages in the CorefUD v1.2 dataset collection.