# Bridging the Preference Gap between Retrievers and LLMs

arXiv: https://arxiv.org/abs/2401.06954 · HTML: https://mlsanity.com/paper/2401.06954/

## Key facts

- Cited by 69 papers 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 23 of its 34 references that are in the map.
- First posted on arXiv 13 Jan 2024.

## Placed in

- Retrieval-augmented generation / [RAG pipeline design and evaluation](https://mlsanity.com/rag/rag-pipeline-design-and-evaluation/)

## Builds on (most cited first, 23 of 23)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [Unsupervised Dense Information Retrieval with Contrastive Learning](https://mlsanity.com/paper/2112.09118/) (2021)
- [Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering](https://mlsanity.com/paper/2007.01282/) (2020)
- [PaLM 2 Technical Report](https://mlsanity.com/paper/2305.10403/) (2023)
- [Atlas: Few-shot Learning with Retrieval Augmented Language Models](https://mlsanity.com/paper/2208.03299/) (2022)
- [Large Language Models Can Be Easily Distracted by Irrelevant Context](https://mlsanity.com/paper/2302.00093/) (2023)
- [Generalization through Memorization: Nearest Neighbor Language Models](https://mlsanity.com/paper/1911.00172/) (2019)
- [REPLUG: Retrieval-Augmented Black-Box Language Models](https://mlsanity.com/paper/2301.12652/) (2023)
- [Large Dual Encoders Are Generalizable Retrievers](https://mlsanity.com/paper/2112.07899/) (2021)
- [RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentation](https://mlsanity.com/paper/2310.04408/) (2023)
- [CONQRR: Conversational Query Rewriting for Retrieval with Reinforcement Learning](https://mlsanity.com/paper/2112.08558/) (2021)
- [Teach LLMs to Personalize -- An Approach inspired by Writing Education](https://mlsanity.com/paper/2308.07968/) (2023)
- [Task-Oriented Query Reformulation with Reinforcement Learning](https://mlsanity.com/paper/1704.04572/) (2017)
- [Boosting Search Engines with Interactive Agents](https://mlsanity.com/paper/2109.00527/) (2021)
- [Pre-computed memory or on-the-fly encoding? A hybrid approach to retrieval augmentation makes the most of your compute](https://mlsanity.com/paper/2301.10448/) (2023)
- [GLIMMER: generalized late-interaction memory reranker](https://mlsanity.com/paper/2306.10231/) (2023)
- [RRAML: Reinforced Retrieval Augmented Machine Learning](https://mlsanity.com/paper/2307.12798/) (2023)

## Built on by (most cited first, 30 of 69)

- [The Power of Noise: Redefining Retrieval for RAG Systems](https://mlsanity.com/paper/2401.14887/) (2024)
- [A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systems](https://mlsanity.com/paper/2504.09037/) (2025)
- [FaithEval: Can Your Language Model Stay Faithful to Context, Even If "The Moon is Made of Marshmallows"](https://mlsanity.com/paper/2410.03727/) (2024)
- [LongRAG: A Dual-Perspective Retrieval-Augmented Generation Paradigm for Long-Context Question Answering](https://mlsanity.com/paper/2410.18050/) (2024)
- [IM-RAG: Multi-Round Retrieval-Augmented Generation Through Learning Inner Monologues](https://mlsanity.com/paper/2405.13021/) (2024)
- [Knowledge Boundary of Large Language Models: A Survey](https://mlsanity.com/paper/2412.12472/) (2024)
- [Improving Retrieval-Augmented Generation through Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2501.15228/) (2025)
- [Parametric Retrieval Augmented Generation](https://mlsanity.com/paper/2501.15915/) (2025)
- [SurveyX: Academic Survey Automation via Large Language Models](https://mlsanity.com/paper/2502.14776/) (2025)
- [Demystifying Domain-adaptive Post-training for Financial LLMs](https://mlsanity.com/paper/2501.04961/) (2025)
- [A Comprehensive Survey on Reinforcement Learning-based Agentic Search: Foundations, Roles, Optimizations, Evaluations, and Applications](https://mlsanity.com/paper/2510.16724/) (2025)
- [SFR-RAG: Towards Contextually Faithful LLMs](https://mlsanity.com/paper/2409.09916/) (2024)
- [Silent Leaks: Implicit Knowledge Extraction Attack on RAG Systems through Benign Queries](https://mlsanity.com/paper/2505.15420/) (2025)
- [Towards AI Search Paradigm](https://mlsanity.com/paper/2506.17188/) (2025)
- [RichRAG: Crafting Rich Responses for Multi-faceted Queries in Retrieval-Augmented Generation](https://mlsanity.com/paper/2406.12566/) (2024)
- [DynamicRAG: Leveraging Outputs of Large Language Model as Feedback for Dynamic Reranking in Retrieval-Augmented Generation](https://mlsanity.com/paper/2505.07233/) (2025)
- [DR-RAG: Applying Dynamic Document Relevance to Retrieval-Augmented Generation for Question-Answering](https://mlsanity.com/paper/2406.07348/) (2024)
- [Bridging Relevance and Reasoning: Rationale Distillation in Retrieval-Augmented Generation](https://mlsanity.com/paper/2412.08519/) (2024)
- [GainRAG: Preference Alignment in Retrieval-Augmented Generation through Gain Signal Synthesis](https://mlsanity.com/paper/2505.18710/) (2025)
- [ARAG: Agentic Retrieval Augmented Generation for Personalized Recommendation](https://mlsanity.com/paper/2506.21931/) (2025)
- [ArgRAG: Explainable Retrieval Augmented Generation using Quantitative Bipolar Argumentation](https://mlsanity.com/paper/2508.20131/) (2025)
- [Beyond Monolithic Architectures: A Multi-Agent Search and Knowledge Optimization Framework for Agentic Search](https://mlsanity.com/paper/2601.04703/) (2026)
- [Preference-Guided Refactored Tuning for Retrieval Augmented Code Generation](https://mlsanity.com/paper/2409.15895/) (2024)
- [Pistis-RAG: Enhancing Retrieval-Augmented Generation with Human Feedback](https://mlsanity.com/paper/2407.00072/) (2024)
- [DeepNote: Note-Centric Deep Retrieval-Augmented Generation](https://mlsanity.com/paper/2410.08821/) (2024)
- [QAgent: A modular Search Agent with Interactive Query Understanding](https://mlsanity.com/paper/2510.08383/) (2025)
- [Awakening Augmented Generation: Learning to Awaken Internal Knowledge of Large Language Models for Question Answering](https://mlsanity.com/paper/2403.15268/) (2024)
- [Improve Dense Passage Retrieval with Entailment Tuning](https://mlsanity.com/paper/2410.15801/) (2024)
- [Inference Scaling for Bridging Retrieval and Augmented Generation](https://mlsanity.com/paper/2412.10684/) (2024)
- [MAO-ARAG: Multi-Agent Orchestration for Adaptive Retrieval-Augmented Generation](https://mlsanity.com/paper/2508.01005/) (2025)

## 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.