mlsanityData to 14 Oct 2026

Supportiveness-based Knowledge Rewriting for Retrieval-augmented Language Modeling

arXiv 2406.08116 ↗First posted 12 Jun 2024cs.CL cs.AIcited by 4

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

Abstract (arXiv)

Retrieval-augmented language models (RALMs) have recently shown great potential in mitigating the limitations of implicit knowledge in LLMs, such as untimely updating of the latest expertise and unreliable retention of long-tail knowledge. However, since the external knowledge base, as well as the retriever, can not guarantee reliability, potentially leading to the knowledge retrieved not being helpful or even misleading for LLM generation. In this paper, we introduce Supportiveness-based Knowledge Rewriting (SKR), a robust and pluggable knowledge rewriter inherently optimized for LLM generation. Specifically, we introduce the novel concept of "supportiveness"--which represents how effectively a knowledge piece facilitates downstream tasks--by considering the perplexity impact of augmented knowledge on the response text of a white-box LLM. Based on knowledge supportiveness, we first design a training data curation strategy for our rewriter model, effectively identifying and filtering out poor or irrelevant rewrites (e.g., with low supportiveness scores) to improve data efficacy. We then introduce the direct preference optimization (DPO) algorithm to align the generated rewrites to optimal supportiveness, guiding the rewriter model to summarize augmented content that better improves the final response. Comprehensive evaluations across six popular knowledge-intensive tasks and four LLMs have demonstrated the effectiveness and superiority of SKR. With only 7B parameters, SKR has shown better knowledge rewriting capability over GPT-4, the current state-of-the-art general-purpose LLM.

Key facts. Cited by 4 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 42 of its 49 references that are in the map. First posted on arXiv 12 Jun 2024.

Builds on

42 of 49 references.

References · 42

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  3. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  4. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  5. 2020Measuring Massive Multitask Language Understandingcited by 7,963
  6. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
  7. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  8. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,955
  9. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,724
  10. 2020Extracting Training Data from Large Language Modelscited by 2,189
  11. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,141
  12. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
30 more
  1. 2018CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledgecited by 1,822
  2. 2018Know What You Don't Know: Unanswerable Questions for SQuADcited by 1,554
  3. 2021Improving language models by retrieving from trillions of tokenscited by 1,293
  4. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,216
  5. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 952
  6. 2019DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphscited by 903
  7. 2019Generalization through Memorization: Nearest Neighbor Language Modelscited by 800
  8. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 792
  9. 2023In-Context Retrieval-Augmented Language Modelscited by 702
  10. 2018CoQA: A Conversational Question Answering Challengecited by 683
  11. 2020KILT: a Benchmark for Knowledge Intensive Language Taskscited by 573
  12. 2023Zephyr: Direct Distillation of LM Alignmentcited by 506
  13. 2023LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compressioncited by 453
  14. 2017Zero-Shot Relation Extraction via Reading Comprehensioncited by 426
  15. 2023Making Retrieval-Augmented Language Models Robust to Irrelevant Contextcited by 369
  16. 2022Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLPcited by 318
  17. 2023LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Modelscited by 287
  18. 2023RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentationcited by 256
  19. 2022Are Large Pre-Trained Language Models Leaking Your Personal Information?cited by 200
  20. 2023RA-DIT: Retrieval-Augmented Dual Instruction Tuningcited by 195
  21. 2023Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Modelscited by 184
  22. 2023Walking Down the Memory Maze: Beyond Context Limit through Interactive Readingcited by 133
  23. 2023How to Train Your DRAGON: Diverse Augmentation Towards Generalizable Dense Retrievalcited by 118
  24. 2023Retrieval meets Long Context Large Language Modelscited by 115
  25. 2023Learning to Filter Context for Retrieval-Augmented Generationcited by 83
  26. 2023Shall We Pretrain Autoregressive Language Models with Retrieval? A Comprehensive Studycited by 63
  27. 2018QuaRel: A Dataset and Models for Answering Questions about Qualitative Relationshipscited by 46
  28. 2021EntQA: Entity Linking as Question Answeringcited by 34
  29. 2024BIDER: Bridging Knowledge Inconsistency for Efficient Retrieval-Augmented LLMs via Key Supporting Evidencecited by 28
  30. 2022DAMO-NLP at NLPCC-2022 Task 2: Knowledge Enhanced Robust NER for Speech Entity Linkingcited by 5

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 3.

4 papers.

  1. 2024Graph Retrieval-Augmented Generation: A Surveycited by 324
  2. 2025SafeRAG: Benchmarking Security in Retrieval-Augmented Generation of Large Language Modelcited by 32
  3. 2025C-3PO: Compact Plug-and-Play Proxy Optimization to Achieve Human-like Retrieval-Augmented Generationcited by 9
  4. 2025On the Diminishing Returns of Complex Robust RAG Training in the Era of Powerful LLMscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Query Rewriting for Retrieval-Augmented Large Language Models
  2. 2025Retrieval Augmented Learning: A Retrial-based Large Language Model Self-Supervised Learning and Autonomous Knowledge Generation
  3. 2025Rethinking LLM Parametric Knowledge as Post-retrieval Confidence for Dynamic Retrieval and Reranking
  4. 2024Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAG
  5. 2024Towards Knowledge Checking in Retrieval-augmented Generation: A Representation Perspective
  6. 2025Direct Retrieval-augmented Optimization: Synergizing Knowledge Selection and Language Models
  7. 2024A + B: A General Generator-Reader Framework for Optimizing LLMs to Unleash Synergy Potential
  8. 2025LLM-Specific Utility for Retrieval-Augmented Generation