mlsanityData to 7 Oct 2026

Bridging the Preference Gap between Retrievers and LLMs

arXiv 2401.06954 ↗First posted 13 Jan 2024cs.CLcited by 69

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

Abstract (arXiv)

Large Language Models (LLMs) have demonstrated superior results across a wide range of tasks, and Retrieval-augmented Generation (RAG) is an effective way to enhance the performance by locating relevant information and placing it into the context window of the LLM. However, the relationship between retrievers and LLMs in a RAG is still under-investigated. Most existing work treats the retriever and the LLM as independent components and leaves a gap between retrieving human-"friendly" information and assembling a LLM-"friendly" context. In this work, we examine a novel bridge mechanism. We validate the ranking and selection assumptions of retrievers in the context of RAG and propose a framework that chains together supervised and reinforcement learning to train a bridge model that optimizes the connection between the retriever and the LLM. Empirical results demonstrate the effectiveness of our method in both question-answering and personalized generation tasks.

Key facts. Cited by 69 papers in the map (data through 7 Oct 2026). Placed in RAG pipeline design and evaluation, one of 15 directions in Retrieval-augmented generation. Builds on 23 of its 34 references that are in the map. First posted on arXiv 13 Jan 2024.

Builds on

23 of 34 references.

References · 23

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  4. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  5. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  6. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  7. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  8. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,203
  9. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,203
  10. 2023PaLM 2 Technical Reportcited by 1,154
  11. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 940
  12. 2023Large Language Models Can Be Easily Distracted by Irrelevant Contextcited by 820
11 more
  1. 2019Generalization through Memorization: Nearest Neighbor Language Modelscited by 788
  2. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 786
  3. 2021Large Dual Encoders Are Generalizable Retrieverscited by 454
  4. 2023RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentationcited by 253
  5. 2021CONQRR: Conversational Query Rewriting for Retrieval with Reinforcement Learningcited by 68
  6. 2023Teach LLMs to Personalize -- An Approach inspired by Writing Educationcited by 48
  7. 2017Task-Oriented Query Reformulation with Reinforcement Learningcited by 39
  8. 2021Boosting Search Engines with Interactive Agentscited by 19
  9. 2023Pre-computed memory or on-the-fly encoding? A hybrid approach to retrieval augmentation makes the most of your computecited by 17
  10. 2023GLIMMER: generalized late-interaction memory rerankercited by 7
  11. 2023RRAML: Reinforced Retrieval Augmented Machine Learningcited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 22; 2025: 29; 2026: 18.

69 papers.

Sort:

By area:

  1. 2024The Power of Noise: Redefining Retrieval for RAG Systemscited by 275
  2. 2025A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systemscited by 108
  3. 2024FaithEval: Can Your Language Model Stay Faithful to Context, Even If "The Moon is Made of Marshmallows"cited by 85
  4. 2024LongRAG: A Dual-Perspective Retrieval-Augmented Generation Paradigm for Long-Context Question Answeringcited by 49
  5. 2024IM-RAG: Multi-Round Retrieval-Augmented Generation Through Learning Inner Monologuescited by 40
  6. 2025Improving Retrieval-Augmented Generation through Multi-Agent Reinforcement Learningcited by 39
  7. 2025Parametric Retrieval Augmented Generationcited by 38
  8. 2024Knowledge Boundary of Large Language Models: A Surveycited by 36
  9. 2025SurveyX: Academic Survey Automation via Large Language Modelscited by 27
  10. 2025Demystifying Domain-adaptive Post-training for Financial LLMscited by 24
  11. 2025A Comprehensive Survey on Reinforcement Learning-based Agentic Search: Foundations, Roles, Optimizations, Evaluations, and Applicationscited by 21
  12. 2024SFR-RAG: Towards Contextually Faithful LLMscited by 19
38 more
  1. 2025Silent Leaks: Implicit Knowledge Extraction Attack on RAG Systems through Benign Queriescited by 19
  2. 2025Towards AI Search Paradigmcited by 19
  3. 2024RichRAG: Crafting Rich Responses for Multi-faceted Queries in Retrieval-Augmented Generationcited by 16
  4. 2024DR-RAG: Applying Dynamic Document Relevance to Retrieval-Augmented Generation for Question-Answeringcited by 14
  5. 2025DynamicRAG: Leveraging Outputs of Large Language Model as Feedback for Dynamic Reranking in Retrieval-Augmented Generationcited by 14
  6. 2024Bridging Relevance and Reasoning: Rationale Distillation in Retrieval-Augmented Generationcited by 13
  7. 2025GainRAG: Preference Alignment in Retrieval-Augmented Generation through Gain Signal Synthesiscited by 12
  8. 2025ARAG: Agentic Retrieval Augmented Generation for Personalized Recommendationcited by 12
  9. 2025ArgRAG: Explainable Retrieval Augmented Generation using Quantitative Bipolar Argumentationcited by 12
  10. 2026Beyond Monolithic Architectures: A Multi-Agent Search and Knowledge Optimization Framework for Agentic Searchcited by 11
  11. 2024Preference-Guided Refactored Tuning for Retrieval Augmented Code Generationcited by 10
  12. 2024Pistis-RAG: Enhancing Retrieval-Augmented Generation with Human Feedbackcited by 8
  13. 2024DeepNote: Note-Centric Deep Retrieval-Augmented Generationcited by 8
  14. 2025QAgent: A modular Search Agent with Interactive Query Understandingcited by 8
  15. 2024Awakening Augmented Generation: Learning to Awaken Internal Knowledge of Large Language Models for Question Answeringcited by 7
  16. 2024Improve Dense Passage Retrieval with Entailment Tuningcited by 7
  17. 2024Inference Scaling for Bridging Retrieval and Augmented Generationcited by 7
  18. 2025MAO-ARAG: Multi-Agent Orchestration for Adaptive Retrieval-Augmented Generationcited by 7
  19. 2026OASES: Outcome-Aligned Search-Evaluation Co-Training for Agentic Searchcited by 7
  20. 2024Contrastive Learning to Improve Retrieval for Real-world Fact Checkingcited by 6
  21. 2024ImageRAG: Enhancing Ultra High Resolution Remote Sensing Imagery Analysis with ImageRAGcited by 6
  22. 2026JADE: Bridging the Strategic-Operational Gap in Dynamic Agentic RAGcited by 6
  23. 2026AffectAgent: Collaborative Multi-Agent Reasoning for Retrieval-Augmented Multimodal Emotion Recognitioncited by 6
  24. 2024Experimenting with Legal AI Solutions: The Case of Question-Answering for Access to Justicecited by 5
  25. 2026SAGEO Arena: A Realistic Environment for Evaluating Search-Augmented Generative Engine Optimizationcited by 5
  26. 2024Familiarity-Aware Evidence Compression for Retrieval-Augmented Generationcited by 4
  27. 2025OpenRAG: Optimizing RAG End-to-End via In-Context Retrieval Learningcited by 4
  28. 2025Leveraging LLM-Assisted Query Understanding for Live Retrieval-Augmented Generationcited by 4
  29. 2026OptiSet: Unified Optimizing Set Selection and Ranking for Retrieval-Augmented Generationcited by 3
  30. 2026Less is More for RAG: Information Gain Pruning for Generator-Aligned Reranking and Evidence Selectioncited by 3
  31. 2026Learning to Retrieve from Agent Trajectoriescited by 3
  32. 2024R^2AG: Incorporating Retrieval Information into Retrieval Augmented Generationcited by 2
  33. 2025Gumbel Reranking: Differentiable End-to-End Reranker Optimizationcited by 2
  34. 2025NAACL2025 Tutorial: Adaptation of Large Language Modelscited by 2
  35. 2025Know3-RAG: A Knowledge-aware RAG Framework with Adaptive Retrieval, Generation, and Filteringcited by 2
  36. 2025Less Is More: Elevating RAG via Performance-Driven Context Compressioncited by 2
  37. 2024Unveiling and Consulting Core Experts in Retrieval-Augmented MoE-based LLMscited by 1
  38. 2025Oreo: A Plug-in Context Reconstructor to Enhance Retrieval-Augmented Generationcited by 1

50 most cited of 69 All 69 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Fine-Grained Guidance for Retrievers: Leveraging LLMs' Feedback in Retrieval-Augmented Generation
  2. 2025LLM-Specific Utility for Retrieval-Augmented Generation
  3. 2024RAGLAB: A Modular and Research-Oriented Unified Framework for Retrieval-Augmented Generation
  4. 2024Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAG
  5. 2025When Retrieval Succeeds and Fails: Rethinking Retrieval-Augmented Generation for LLMs
  6. 2025Optimizing Knowledge Integration in Retrieval-Augmented Generation with Self-Selection
  7. 2025Tuning LLMs by RAG Principles: Towards LLM-native Memory
  8. 2025Retrieval-Augmented Generation: A Comprehensive Survey of Architectures, Enhancements, and Robustness Frontiers