# [Lions: 1] and [Tigers: 2] and [Bears: 3], Oh My! Literary Coreference Annotation with LLMs

arXiv: https://arxiv.org/abs/2401.17922 · HTML: https://mlsanity.com/paper/2401.17922/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 27 references that are in the map.
- First posted on arXiv 31 Jan 2024.

## Builds on (most cited first, 19 of 19)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [mT5: A massively multilingual pre-trained text-to-text transformer](https://mlsanity.com/paper/2010.11934/) (2020)
- [Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling](https://mlsanity.com/paper/2304.01373/) (2023)
- [End-to-end Neural Coreference Resolution](https://mlsanity.com/paper/1707.07045/) (2017)
- [BERT for Coreference Resolution: Baselines and Analysis](https://mlsanity.com/paper/1908.09091/) (2019)
- [Coreference Resolution as Query-based Span Prediction](https://mlsanity.com/paper/1911.01746/) (2019)
- [Coreferential Reasoning Learning for Language Representation](https://mlsanity.com/paper/2004.06870/) (2020)
- [Deep Reinforcement Learning for Mention-Ranking Coreference Models](https://mlsanity.com/paper/1609.08667/) (2016)
- [An Annotated Dataset of Coreference in English Literature](https://mlsanity.com/paper/1912.01140/) (2019)
- [Modeling Protagonist Emotions for Emotion-Aware Storytelling](https://mlsanity.com/paper/2010.06822/) (2020)
- [Movie Plot Analysis via Turning Point Identification](https://mlsanity.com/paper/1908.10328/) (2019)
- [Coreference Resolution through a seq2seq Transition-Based System](https://mlsanity.com/paper/2211.12142/) (2022)
- [LingMess: Linguistically Informed Multi Expert Scorers for Coreference Resolution](https://mlsanity.com/paper/2205.12644/) (2022)
- [F-coref: Fast, Accurate and Easy to Use Coreference Resolution](https://mlsanity.com/paper/2209.04280/) (2022)
- [Are Large Language Models Robust Coreference Resolvers?](https://mlsanity.com/paper/2305.14489/) (2023)
- [Few-Shot Anaphora Resolution in Scientific Protocols via Mixtures of In-Context Experts](https://mlsanity.com/paper/2210.03690/) (2022)
- [Seq2seq is All You Need for Coreference Resolution](https://mlsanity.com/paper/2310.13774/) (2023)
- [A Benchmark of Rule-Based and Neural Coreference Resolution in Dutch Novels and News](https://mlsanity.com/paper/2011.01615/) (2020)
- [Better Handling Coreference Resolution in Aspect Level Sentiment Classification by Fine-Tuning Language Models](https://mlsanity.com/paper/2307.05646/) (2023)

## Built on by (most cited first, 8 of 8)

- [Findings of the Fourth Shared Task on Multilingual Coreference Resolution: Can LLMs Dethrone Traditional Approaches?](https://mlsanity.com/paper/2509.17796/) (2025)
- [Referential ambiguity and clarification requests: comparing human and LLM behaviour](https://mlsanity.com/paper/2507.10445/) (2025)
- [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)
- [Says Who? Effective Zero-Shot Annotation of Focalization](https://mlsanity.com/paper/2409.11390/) (2024)
- [Generating Visual Stories with Grounded and Coreferent Characters](https://mlsanity.com/paper/2409.13555/) (2024)
- [Evaluating Prompt-Based and Fine-Tuned Approaches to Czech Anaphora Resolution](https://mlsanity.com/paper/2506.18091/) (2025)
- [FineREX: Fine-Tuned NER-RE for Human Smuggling Knowledge Graphs](https://mlsanity.com/paper/2606.19710/) (2026)

## Abstract (arXiv)

Coreference annotation and resolution is a vital component of computational literary studies. However, it has previously been difficult to build high quality systems for fiction. Coreference requires complicated structured outputs, and literary text involves subtle inferences and highly varied language. New language-model-based seq2seq systems present the opportunity to solve both these problems by learning to directly generate a copy of an input sentence with markdown-like annotations. We create, evaluate, and release several trained models for coreference, as well as a workflow for training new models.