mlsanityData to 14 Oct 2026

From Ambiguity to Accuracy: The Transformative Effect of Coreference Resolution on Retrieval-Augmented Generation systems

arXiv 2507.07847 ↗First posted 10 Jul 2025cs.CL cs.AIcited by 0

On the map: Retrieval-augmented generation → RAG pipeline design and evaluation

Abstract (arXiv)

Retrieval-Augmented Generation (RAG) has emerged as a crucial framework in natural language processing (NLP), improving factual consistency and reducing hallucinations by integrating external document retrieval with large language models (LLMs). However, the effectiveness of RAG is often hindered by coreferential complexity in retrieved documents, introducing ambiguity that disrupts in-context learning. In this study, we systematically investigate how entity coreference affects both document retrieval and generative performance in RAG-based systems, focusing on retrieval relevance, contextual understanding, and overall response quality. We demonstrate that coreference resolution enhances retrieval effectiveness and improves question-answering (QA) performance. Through comparative analysis of different pooling strategies in retrieval tasks, we find that mean pooling demonstrates superior context capturing ability after applying coreference resolution. In QA tasks, we discover that smaller models benefit more from the disambiguation process, likely due to their limited inherent capacity for handling referential ambiguity. With these findings, this study aims to provide a deeper understanding of the challenges posed by coreferential complexity in RAG, providing guidance for improving retrieval and generation in knowledge-intensive AI applications.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RAG pipeline design and evaluation, one of 15 directions in Retrieval-augmented generation. Builds on 19 of its 35 references that are in the map. First posted on arXiv 10 Jul 2025.

Builds on

19 of 35 references.

References · 19

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2019BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questionscited by 2,183
  3. 2024Gemma 2: Improving Open Language Models at a Practical Sizecited by 1,998
  4. 2018Know What You Don't Know: Unanswerable Questions for SQuADcited by 1,554
  5. 2022Text Embeddings by Weakly-Supervised Contrastive Pre-trainingcited by 1,253
  6. 2023Large Language Models Can Be Easily Distracted by Irrelevant Contextcited by 841
  7. 2023Towards General Text Embeddings with Multi-stage Contrastive Learningcited by 723
  8. 2024NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Modelscited by 472
  9. 2020SPECTER: Document-level Representation Learning using Citation-informed Transformerscited by 430
  10. 2024LLM2Vec: Large Language Models Are Secretly Powerful Text Encoderscited by 404
  11. 2023The Belebele Benchmark: a Parallel Reading Comprehension Dataset in 122 Language Variantscited by 311
  12. 2017End-to-end Neural Coreference Resolutioncited by 241
7 more
  1. 2024mGTE: Generalized Long-Context Text Representation and Reranking Models for Multilingual Text Retrievalcited by 236
  2. 2024Jasper and Stella: distillation of SOTA embedding modelscited by 112
  3. 2019Quoref: A Reading Comprehension Dataset with Questions Requiring Coreferential Reasoningcited by 100
  4. 2023Large Language Models in Education: Vision and Opportunitiescited by 54
  5. 2022Prompting Language Models for Linguistic Structurecited by 39
  6. 2024Bridging Context Gaps: Leveraging Coreference Resolution for Long Contextual Understandingcited by 16
  7. 2020Coreference Reasoning in Machine Reading Comprehensioncited by 6

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025A Survey on Knowledge-Oriented Retrieval-Augmented Generation
  2. 2025Enhancing Retrieval-Augmented Generation: A Study of Best Practices
  3. 2024A Comprehensive Survey of Retrieval-Augmented Generation (RAG): Evolution, Current Landscape and Future Directions
  4. 2024Retrieval-Augmented Generation for Natural Language Processing: A Survey
  5. 2025Grounding Long-Context Reasoning with Contextual Normalization for Retrieval-Augmented Generation
  6. 2024Evaluation of Retrieval-Augmented Generation: A Survey
  7. 2025Dynamic Context Selection for Retrieval-Augmented Generation: Mitigating Distractors and Positional Bias
  8. 2024The Power of Noise: Redefining Retrieval for RAG Systems