# Improving LLMs' Learning for Coreference Resolution

arXiv: https://arxiv.org/abs/2509.11466 · HTML: https://mlsanity.com/paper/2509.11466/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 31 references that are in the map.
- First posted on arXiv 14 Sep 2025.

## Builds on (most cited first, 15 of 15)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [SpanBERT: Improving Pre-training by Representing and Predicting Spans](https://mlsanity.com/paper/1907.10529/) (2019)
- [The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"](https://mlsanity.com/paper/2309.12288/) (2023)
- [End-to-end Neural Coreference Resolution](https://mlsanity.com/paper/1707.07045/) (2017)
- [Large Language Models are Few-Shot Clinical Information Extractors](https://mlsanity.com/paper/2205.12689/) (2022)
- [Higher-order Coreference Resolution with Coarse-to-fine Inference](https://mlsanity.com/paper/1804.05392/) (2018)
- [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)
- [Improving Coreference Resolution by Learning Entity-Level Distributed Representations](https://mlsanity.com/paper/1606.01323/) (2016)
- [Reverse Training to Nurse the Reversal Curse](https://mlsanity.com/paper/2403.13799/) (2024)
- [Coreference Resolution through a seq2seq Transition-Based System](https://mlsanity.com/paper/2211.12142/) (2022)
- [A Cluster Ranking Model for Full Anaphora Resolution](https://mlsanity.com/paper/1911.09532/) (2019)
- [Seq2seq is All You Need for Coreference Resolution](https://mlsanity.com/paper/2310.13774/) (2023)
- [CoGen: Learning from Feedback with Coupled Comprehension and Generation](https://mlsanity.com/paper/2408.15992/) (2024)

## Built on by (most cited first, 1 of 1)

- [Flout at Your Own Risk: LLMs Struggle with Pragmatic Cooperativity Under Epistemic Asymmetry](https://mlsanity.com/paper/2607.11053/) (2026)

## Abstract (arXiv)

Coreference Resolution (CR) is crucial for many NLP tasks, but existing LLMs struggle with hallucination and under-performance. In this paper, we investigate the limitations of existing LLM-based approaches to CR-specifically the Question-Answering (QA) Template and Document Template methods and propose two novel techniques: Reversed Training with Joint Inference and Iterative Document Generation. Our experiments show that Reversed Training improves the QA Template method, while Iterative Document Generation eliminates hallucinations in the generated source text and boosts coreference resolution. Integrating these methods and techniques offers an effective and robust solution to LLM-based coreference resolution.