CorefInst: Leveraging LLMs for Multilingual Coreference Resolution (2026.tacl-1)

Copied to clipboard

Challenge: Existing methods for CR are encoder-only, decoder-based and asynchronous models.
Approach: They propose a multilingual CR methodology which leverages decoder-only LLMs to handle overt and zero mentions.
Outcome: The proposed model outperforms the leading multilingual CR model by 2 percentage points across all languages in the CorefUD v1.2 dataset.

Similar Papers

A Controlled Reevaluation of Coreference Resolution Models (2024.lrec-main)

Copied to clipboard

Challenge: a pretrained language model is used in state-of-the-art coreference resolution models.
Approach: They evaluate five coreference resolution models and control for language model used . they find that encoder-based CR models outperform decoder--based models in accuracy .
Outcome: The encoder-based model outperforms the decoder--based models in accuracy and speed . older model generalizes the best to out-of-domain textual genres .
ImCoref-CeS: An Improved Lightweight Pipeline for Coreference Resolution with LLM-based Checker-Splitter Refinement (2026.acl-long)

Copied to clipboard

Challenge: Existing supervised neural methods for coreference resolution are underexplored . current methods rely on small language models, but their potential is underexploited .
Approach: They propose a framework that integrates an enhanced supervised model with LLM-based reasoning.
Outcome: The proposed method surpasses existing state-of-the-art methods in coreference resolution.
Investigating Multilingual Coreference Resolution by Universal Annotations (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing systems for multilingual coreference resolution have been challenging due to linguistic diversity and complexity of different languages.
Approach: They propose a multilingual coreference dataset with universal morphosyntactic and coreference annotations.
Outcome: The proposed dataset improves the baseline system by 0.9% . the proposed dataset is based on the framework of Universal Dependencies 2 .
Z-coref: Thai Coreference and Zero Pronoun Resolution (2024.acl-srw)

Copied to clipboard

Challenge: limited research and datasets pose significant challenges in Thai language . a proposed model capable of simultaneously handling CR and ZPR tasks takes less time to train .
Approach: They propose to annotate a Thai-based CR and ZPR dataset and introduce a model that can handle both tasks by adjusting the span definition to include token gaps.
Outcome: The proposed model outperforms the state-of-the-art in resolving both coreference resolution and zero-pronoun resolution while taking less time to train.
Assessing the Capabilities of Large Language Models in Coreference: An Evaluation (2024.lrec-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) are a new approach to coreference resolution, but their performance is not yet fully understood.
Approach: They propose that future efforts should improve scope, data, and evaluation methods of traditional coreference research to adapt to the development of LLMs.
Outcome: The proposed methods improve scope, data, and evaluation methods of traditional coreference research to adapt to the development of LLMs.
NovelCR: A Large-Scale Bilingual Dataset Tailored for Long-Span Coreference Resolution (2025.findings-acl)

Copied to clipboard

Challenge: Existing coreference resolution datasets are either small in scale or restrict coreference to a limited text span.
Approach: They present a large-scale bilingual benchmark for long-span coreference resolution . they find that NovelCR is notably rich in long-spanning coreference pairs .
Outcome: The proposed benchmark is rich in long-span coreference pairs and notably low baselines.
CorefUD 1.0: Coreference Meets Universal Dependencies (2022.lrec-1)

Copied to clipboard

Challenge: Recent advances in standardization for annotated language resources have led to successful large scale efforts, such as the Universal Dependencies (UD) project for multilingual syntactically annotized data.
Approach: They propose a multilingual collection of corpora and a standardized format for coreference resolution compatible with morphosyntactic annotations in the UD framework.
Outcome: The proposed framework is compatible with morphosyntactic annotations and includes facilities for related tasks such as named entity recognition.
Correct-Detect: Balancing Performance and Ambiguity Through the Lens of Coreference Resolution in LLMs (2025.emnlp-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) are intended to reflect human linguistic competencies . but when context is absent or insufficient, ambiguity resolution becomes more tenuous .
Approach: They propose a CORRECT-DETECT trade-off between large language models and ambiguity detection . they show that large language model models can achieve good performance with minimal prompting .
Outcome: The proposed models can achieve good performance with minimal prompting in coreference disambiguation and detection of ambiguity in corefertility tasks, but they cannot do both at the same time.
Maverick: Efficient and Accurate Coreference Resolution Defying Recent Trends (2024.acl-long)

Copied to clipboard

Challenge: Large autoregressive generative models have emerged as the cornerstone for achieving the highest performance across several Natural Language Processing tasks.
Approach: They propose a pipeline that trains a state-of-the-art Coreference Resolution system within the constraints of an academic budget and trains with up to 0.006x the memory resources.
Outcome: The proposed framework outperforms encoder-based discriminative systems on the CoNLL-2012 benchmark, training with up to 0.006x the memory resources and obtaining 170x faster inference compared to previous state-of-the-art systems.
Coreference Resolution through a seq2seq Transition-Based System (2023.tacl-1)

Copied to clipboard

Challenge: Recent coreference resolution systems use search algorithms to identify mentions and resolve coreference.
Approach: They propose a text-to-text coreference resolution system that uses a semantic paradigm to predict mentions and links jointly.
Outcome: The proposed system achieves state-of-the-art accuracy on CoNLL-2012 datasets with 83.3 F1-score for English, 68.5 F1 score for Arabic, and 74.3 F1 scores for Chinese.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations