mlsanityData to 14 Oct 2026

Oreo: A Plug-in Context Reconstructor to Enhance Retrieval-Augmented Generation

arXiv 2502.13019 ↗First posted 18 Feb 2025cs.CLcited by 1

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

Abstract (arXiv)

Retrieval-Augmented Generation (RAG) aims to augment the capabilities of Large Language Models (LLMs) by retrieving and incorporate external documents or chunks prior to generation. However, even improved retriever relevance can brings erroneous or contextually distracting information, undermining the effectiveness of RAG in downstream tasks. We introduce a compact, efficient, and pluggable module designed to refine retrieved chunks before using them for generation. The module aims to extract and reorganize the most relevant and supportive information into a concise, query-specific format. Through a three-stage training paradigm - comprising supervised fine - tuning, contrastive multi-task learning, and reinforcement learning-based alignment - it prioritizes critical knowledge and aligns it with the generator's preferences. This approach enables LLMs to produce outputs that are more accurate, reliable, and contextually appropriate.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in RAG pipeline design and evaluation, one of 15 directions in Retrieval-augmented generation. Builds on 74 of its 125 references that are in the map. First posted on arXiv 18 Feb 2025.

Builds on

74 of 125 references.

Closest ancestors · 7

Same direction, newest first

  1. 2024Stochastic RAG: End-to-End Retrieval-Augmented Generation through Expected Utility Maximization5 May
  2. 2024The Power of Noise: Redefining Retrieval for RAG Systems26 Jan
  3. 2024Bridging the Preference Gap between Retrievers and LLMs13 Jan
  4. 2023Retrieval-Augmented Generation for Large Language Models: A Survey18 Dec
  5. 2023RETA-LLM: A Retrieval-Augmented Large Language Model Toolkit8 Jun
  6. 2022FiD-Light: Efficient and Effective Retrieval-Augmented Text Generation28 Sep
  7. 2022A Survey on Retrieval-Augmented Text Generation2 Feb

Other references · 67

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  3. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  4. 2024Qwen2.5 Technical Reportcited by 4,942
  5. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  6. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  7. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,720
  8. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  9. 2022Scaling Instruction-Finetuned Language Modelscited by 3,024
  10. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,955
  11. 2020Learning to summarize from human feedbackcited by 2,588
  12. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,141
38 more
  1. 2024A Survey on LLM-as-a-Judgecited by 1,423
  2. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,282
  3. 2020ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERTcited by 1,178
  4. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,128
  5. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 952
  6. 2022STaR: Bootstrapping Reasoning With Reasoningcited by 940
  7. 2020On Faithfulness and Factuality in Abstractive Summarizationcited by 900
  8. 2023Large Language Models Can Be Easily Distracted by Irrelevant Contextcited by 841
  9. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 792
  10. 2024Generative Verifiers: Reward Modeling as Next-Token Predictioncited by 480
  11. 2021ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interactioncited by 476
  12. 2023LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compressioncited by 453
  13. 2022RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learningcited by 366
  14. 2023Adapting Language Models to Compress Contextscited by 356
  15. 2024LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compressioncited by 348
  16. 2023Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergycited by 346
  17. 2023Large Language Models for Information Retrieval: A Surveycited by 331
  18. 2021Recursively Summarizing Books with Human Feedbackcited by 290
  19. 2023LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Modelscited by 287
  20. 2024Knowledge Conflicts for LLMs: A Surveycited by 283
  21. 2022Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimizationcited by 246
  22. 2022OPT-IML: Scaling Language Model Instruction Meta Learning through the Lens of Generalizationcited by 236
  23. 2019Multi-Stage Document Ranking with BERTcited by 201
  24. 2023Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Modelscited by 184
  25. 2023RankZephyr: Effective and Robust Zero-Shot Listwise Reranking is a Breeze!cited by 155
  26. 2020Detecting Hallucinated Content in Conditional Neural Sequence Generationcited by 152
  27. 2023Query2doc: Query Expansion with Large Language Modelscited by 149
  28. 2023Large Language Model Is Not a Good Few-shot Information Extractor, but a Good Reranker for Hard Samples!cited by 119
  29. 2024Survey on Large Language Model-Enhanced Reinforcement Learning: Concept, Taxonomy, and Methodscited by 116
  30. 2022RankT5: Fine-Tuning T5 for Text Ranking with Ranking Lossescited by 115
  31. 2022Re2G: Retrieve, Rerank, Generatecited by 102
  32. 2024OffsetBias: Leveraging Debiased Data for Tuning Evaluatorscited by 94
  33. 2024β-DPO: Direct Preference Optimization with Dynamic βcited by 90
  34. 2023Unlocking Context Constraints of LLMs: Enhancing Context Efficiency of LLMs with Self-Information-Based Content Filteringcited by 65
  35. 2024CompAct: Compressing Retrieved Documents Actively for Question Answeringcited by 64
  36. 2024Don't Forget to Connect! Improving RAG with Graph-based Rerankingcited by 49
  37. 2021Measuring and Increasing Context Usage in Context-Aware Machine Translationcited by 48
  38. 2023Tree of Clarifications: Answering Ambiguous Questions with Retrieval-Augmented Large Language Modelscited by 43

50 most cited of 67 All 67 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Experience as a Compass: Multi-agent RAG with Evolving Orchestration and Agent Promptscited by 3

Similar, not cited

Close in wording, no citation either way

  1. 2025Enhancing Retrieval-Augmented Generation: A Study of Best Practices
  2. 2025Dynamic Context Selection for Retrieval-Augmented Generation: Mitigating Distractors and Positional Bias
  3. 2025Retrieval-Augmented Generation: A Comprehensive Survey of Architectures, Enhancements, and Robustness Frontiers
  4. 2024RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generation
  5. 2025When Retrieval Succeeds and Fails: Rethinking Retrieval-Augmented Generation for LLMs
  6. 2026Mapping the RAG Landscape: A Four Axis Taxonomy of Efficiency, Defense, Interactivity, and Reasoning
  7. 2024A Survey on Retrieval-Augmented Text Generation for Large Language Models
  8. 2024Contextual Compression in Retrieval-Augmented Generation for Large Language Models: A Survey