mlsanityData to 7 Oct 2026

Read the Docs Before Rewriting: Equip Rewriter with Domain Knowledge via Continual Pre-training

arXiv 2507.00477 ↗First posted 1 Jul 2025cs.IRcited by 1

On the map: Retrieval-augmented generation → RAG robustness and adaptive retrieval

Abstract (arXiv)

A Retrieval-Augmented Generation (RAG)-based question-answering (QA) system enhances a large language model's knowledge by retrieving relevant documents based on user queries. Discrepancies between user queries and document phrasings often necessitate query rewriting. However, in specialized domains, the rewriter model may struggle due to limited domain-specific knowledge. To resolve this, we propose the R&R (Read the doc before Rewriting) rewriter, which involves continual pre-training on professional documents, akin to how students prepare for open-book exams by reviewing textbooks. Additionally, it can be combined with supervised fine-tuning for improved results. Experiments on multiple datasets demonstrate that R&R excels in professional QA across multiple domains, effectively bridging the query-document gap, while maintaining good performance in general scenarios, thus advancing the application of RAG-based QA systems in specialized fields.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation. Builds on 24 of its 31 references that are in the map. First posted on arXiv 1 Jul 2025.

Builds on

24 of 31 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generation31 Mar

Other references · 23

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  3. 2024LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Modelscited by 1,442
  4. 2019PubMedQA: A Dataset for Biomedical Research Question Answeringcited by 1,271
  5. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,203
  6. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,203
  7. 2020ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERTcited by 1,160
  8. 2017Reading Wikipedia to Answer Open-Domain Questionscited by 777
  9. 2021Learning To Retrieve Prompts for In-Context Learningcited by 641
  10. 2022Precise Zero-Shot Dense Retrieval without Relevance Labelscited by 508
  11. 2020AmbigQA: Answering Ambiguous Open-domain Questionscited by 385
  12. 2023Making Retrieval-Augmented Language Models Robust to Irrelevant Contextcited by 364
11 more
  1. 2022One Embedder, Any Task: Instruction-Finetuned Text Embeddingscited by 329
  2. 2022Generate rather than Retrieve: Large Language Models are Strong Context Generatorscited by 296
  3. 2024When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Methodcited by 201
  4. 2024RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMscited by 200
  5. 2023LawBench: Benchmarking Legal Knowledge of Large Language Modelscited by 111
  6. 2021CONQRR: Conversational Query Rewriting for Retrieval with Reinforcement Learningcited by 68
  7. 2024FinTextQA: A Dataset for Long-form Financial Question Answeringcited by 54
  8. 2024RaFe: Ranking Feedback Improves Query Rewriting for RAGcited by 47
  9. 2023IterCQR: Iterative Conversational Query Reformulation with Retrieval Guidancecited by 20
  10. 2024SyllabusQA: A Course Logistics Question Answering Datasetcited by 9
  11. 2023Augmenting Zero-Shot Dense Retrievers with Plug-in Mixture-of-Memoriescited by 6

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Sensorium Arc: AI Agent System for Oceanic Data Exploration and Interactive Eco-Artcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Align Documents to Questions: Question-Oriented Document Rewriting for Retrieval-Augmented Generation
  2. 2024DMQR-RAG: Diverse Multi-Query Rewriting for RAG
  3. 2024Retrieval-Augmented Generation for Domain-Specific Question Answering: A Case Study on Pittsburgh and CMU
  4. 2024Enhancing Retrieval and Managing Retrieval: A Four-Module Synergy for Improved Quality and Efficiency in RAG Systems
  5. 2024RE-RAG: Improving Open-Domain QA Performance and Interpretability with Relevance Estimator in Retrieval-Augmented Generation
  6. 2026Better Together: Complementary Query Rewriting Under a Strong RAG Baseline
  7. 2025PreQRAG -- Classify and Rewrite for Enhanced RAG
  8. 2024DR-RAG: Applying Dynamic Document Relevance to Retrieval-Augmented Generation for Question-Answering