mlsanityData to 7 Oct 2026

Optimizing Knowledge Integration in Retrieval-Augmented Generation with Self-Selection

arXiv 2502.06148 ↗First posted 10 Feb 2025cs.CL cs.IRcited by 2

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

Abstract (arXiv)

Retrieval-Augmented Generation (RAG), which integrates external knowledge into Large Language Models (LLMs), has proven effective in enabling LLMs to produce more accurate and reliable responses. However, it remains a significant challenge how to effectively integrate external retrieved knowledge with internal parametric knowledge in LLMs. In this work, we propose a novel Self-Selection RAG framework, where the LLM is made to select from pairwise responses generated with internal parametric knowledge solely and with external retrieved knowledge together to achieve enhanced accuracy. To this end, we devise a Self-Selection-RGP method to enhance the capabilities of the LLM in both generating and selecting the correct answer, by training the LLM with Direct Preference Optimization (DPO) over a curated Retrieval Generation Preference (RGP) dataset. Experimental results with two open-source LLMs (i.e., Llama2-13B-Chat and Mistral-7B) well demonstrate the superiority of our approach over other baseline methods on Natural Questions (NQ) and TrivialQA datasets.

Key facts. Cited by 2 papers 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 32 of its 46 references that are in the map. First posted on arXiv 10 Feb 2025.

Builds on

32 of 46 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity21 Mar
  2. 2024RA-ISF: Learning to Answer and Understand from Retrieval Augmentation via Iterative Self-Feedback11 Mar
  3. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection17 Oct

Other references · 29

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  3. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  4. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,115
  5. 2017Deep reinforcement learning from human preferencescited by 3,846
  6. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  7. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  8. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
  9. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  10. 2019Fine-Tuning Language Models from Human Preferencescited by 2,124
  11. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,722
  12. 2018Know What You Don't Know: Unanswerable Questions for SQuADcited by 1,538
17 more
  1. 2023FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generationcited by 1,259
  2. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 911
  3. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 786
  4. 2017Crowdsourcing Multiple Choice Science Questionscited by 742
  5. 2023In-Context Retrieval-Augmented Language Modelscited by 694
  6. 2019Latent Retrieval for Weakly Supervised Open Domain Question Answeringcited by 691
  7. 2023RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedbackcited by 615
  8. 2020Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillationcited by 591
  9. 2023C-Pack: Packed Resources For General Chinese Embeddingscited by 556
  10. 2019Neural Text Generation with Unlikelihood Trainingcited by 489
  11. 2022RealTime QA: What's the Answer Right Now?cited by 239
  12. 2024Optimization Methods for Personalizing Large Language Models through Retrieval Augmentationcited by 98
  13. 2023Search-in-the-Chain: Interactively Enhancing Large Language Models with Search for Knowledge-intensive Taskscited by 73
  14. 2024SuRe: Summarizing Retrievals using Answer Candidates for Open-domain QA of LLMscited by 67
  15. 2023Merging Generated and Retrieved Knowledge for Open-Domain QAcited by 36
  16. 2024Measuring and Enhancing Trustworthiness of LLMs in RAG through Grounded Attributions and Learning to Refusecited by 33
  17. 2023Knowledgeable Preference Alignment for LLMs in Domain-specific Question Answeringcited by 28

Built on by

Cited by year

Citing papers per year: 2025: 2.

2 papers.

  1. 2025Retrieval is Not Enough: Enhancing RAG Reasoning through Test-Time Critique and Optimizationcited by 5
  2. 2025MuISQA: Multi-Intent Retrieval-Augmented Generation for Scientific Question Answeringcited by 2

Similar, not cited

Close in wording, no citation either way

  1. 2025Self-Routing RAG: Binding Selective Retrieval with Knowledge Verbalization
  2. 2025Adaptive Retrieval Without Self-Knowledge? Bringing Uncertainty Back Home
  3. 2025A Survey on Knowledge-Oriented Retrieval-Augmented Generation
  4. 2024R^2AG: Incorporating Retrieval Information into Retrieval Augmented Generation
  5. 2024A Comprehensive Survey of Retrieval-Augmented Generation (RAG): Evolution, Current Landscape and Future Directions
  6. 2024Bridging the Preference Gap between Retrievers and LLMs
  7. 2024Multi-Source Knowledge Pruning for Retrieval-Augmented Generation: A Benchmark and Empirical Study
  8. 2025Dynamic and Parametric Retrieval-Augmented Generation