Bridging Context Gaps: Leveraging Coreference Resolution for Long Contextual Understanding
Yanming Liu, Xinyue Peng, Jiannan Cao, Shi Bo, Yanxin Shen, Tianyu Du, Sheng Cheng, Xun Wang, Jianwei Yin, Xuhong Zhang
Abstract
Large language models (LLMs) have shown remarkable capabilities in natural language processing; however, they still face difficulties when tasked with understanding lengthy contexts and executing effective question answering. These challenges often arise due to the complexity and ambiguity present in longer texts. To enhance the performance of LLMs in such scenarios, we introduce the Long Question Coreference Adaptation (LQCA) method. This innovative framework focuses on coreference resolution tailored to long contexts, allowing the model to identify and manage references effectively. The LQCA method encompasses four key steps: resolving coreferences within sub-documents, computing the distances between mentions, defining a representative mention for coreference, and answering questions through mention replacement. By processing information systematically, the framework provides easier-to-handle partitions for LLMs, promoting better understanding. Experimental evaluations on a range of LLMs and datasets have yielded positive results, with a notable improvements on OpenAI-o1mini and GPT-4o models, highlighting the effectiveness of leveraging coreference resolution to bridge context gaps in question answering. Our code is public at https://github.com/OceannTwT/LQCA.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
4 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- Deberta: decoding-Enhanced Bert with Disentangled Attention cites Language Models are Few-Shot Learners
- Correct-Detect: Balancing Performance and Ambiguity Through the Lens of Coreference Resolution in LLMs cites Language Models are Few-Shot Learners
- Large Language Models are Zero-Shot Reasoners cites Language Models are Few-Shot Learners
- Large Language Models are Zero-Shot Reasoners cites Training language models to follow instructions with human feedback
- Language Models are Few-Shot Learners cites Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
- Training language models to follow instructions with human feedback cites Language Models are Few-Shot Learners
Cited by top-tier papers4
- StepFly: Agentic Troubleshooting Guide Automation for Incident DiagnosisJiayi Mao, Liqun Li, Yanjie Gao, Zegang Peng et al.FSE 2026 · 1 citation
- KG-CQR: Leveraging Structured Relation Representations in Knowledge Graphs for Contextual Query RetrievalChi Minh Bui, Ngoc Mai Thieu, Van Vinh Nguyen, Jason J. Jung et al.EMNLP 2025 · 1 citation
- Correct-Detect: Balancing Performance and Ambiguity Through the Lens of Coreference Resolution in LLMsAmber Shore, Russell Scheinberg, Ameeta Agrawal, So Young LeeEMNLP 2025
- xCoRe: Cross-context Coreference ResolutionGiuliano Martinelli, Bruno Gatti, Roberto NavigliEMNLP 2025
Builds on19
- Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah et al.NeurIPS 2020 · 64,255 citations
- Training language models to follow instructions with human feedbackLong Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida et al.NeurIPS 2022 · 24,707 citations
- Retrieval-Augmented Generation for Knowledge-Intensive NLP TasksPatrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni et al.NeurIPS 2020 · 19,162 citations
- Large Language Models are Zero-Shot ReasonersTakeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo et al.NeurIPS 2022 · 8,168 citations
- Deberta: decoding-Enhanced Bert with Disentangled AttentionPengcheng He, Xiaodong Liu, Jianfeng Gao, Weizhu ChenICLR 2021 · 3,729 citations
Related papers
- ImCoref-CeS: An Improved Lightweight Pipeline for Coreference Resolution with LLM-based Checker-Splitter RefinementKangyang Luo, Yuzhuo Bai, Shuzheng Si, Cheng Gao et al.ACL 2026 · 1 citation
- LLoCO: Learning Long Contexts OfflineSijun Tan, Xiuyu Li, Shishir G. Patil, Ziyang Wu et al.EMNLP 2024 · 3 citations
- LONGAGENT: Achieving Question Answering for 128k-Token-Long Documents through Multi-Agent CollaborationJun Zhao, Can Zu, Xu Hao, Yi Lu et al.EMNLP 2024 · 5 citations
- Ref-Long: Benchmarking the Long-context Referencing Capability of Long-context Language ModelsJunjie Wu, Gefei Gu, Yanan Zheng, Dit-Yan Yeung et al.ACL 2025 · 4 citations
- Identifying Query-Relevant Neurons in Large Language Models for Long-Form TextsLihu Chen, Adam Dejl, Francesca ToniAAAI 2025 · 15 citations
