mlsanityData to 7 Oct 2026

Generation and context integration

407 papers3 this weekLow confidence in this grouping: the papers may belong to more than one topic, or the group may changeLow confidence in this grouping: the papers may belong to more than one topic, or the group may change · About

Keywords: language, retrieval, retrieval-augmented, generation, context

Key facts. Generation and context integration: 407 papers on arXiv since 2020 (data through 7 Oct 2026). 254 of its 407 mapped papers (62%) cite “Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks” (2020, arXiv 2005.11401). 107 of its 407 mapped papers (26%) cite “REALM: Retrieval-Augmented Language Model Pre-Training” (2020, arXiv 2002.08909). 14 new papers 17 Sep–7 Oct.

What’s new

17 Sep – 7 Oct 2026

14 new papers, 17 Sep – 7 Oct; 3 this week.

  1. This week · 3
  2. Does Document Structure Help Dense Retrieval? A Placebo-Controlled Ablation of Four Mechanisms Across Two Corpora also fits: Multimodal RAG
  3. EntroPrefill: Renyi-Guided Context Pruning with Conditional Stability Guarantees for Retrieval-Augmented Generation
  4. UNREAL: Unifying Retrieval and Long-Context with a Single Model also fits: RAG robustness and adaptive retrieval
  5. Earlier · 11
  6. Principled Top-k Selection for Language Models with Hybrid Gradients
  7. CacheRepair: Learning to Repair Cross-Chunk Context in RAG for KV Cache Fusion
  8. RelaxKV: Recomputation Guided by the Query with Sparse Context Attention for Efficient KV Cache Reuse
  9. When Does Dense Retrieval Need Asymmetric Geometry? A Bias-Variance Theory of Shared and Dual Projections also fits: Vector search and ANN indexes
  10. Beyond the Context Window: An Adaptive Entropy-Based Routing Framework for Hybrid Retrieval and Long-Context Language Models also fits: RAG robustness and adaptive retrieval
  11. MORSE: Multi-Context Ordering via Reverse Scoring for Evidence-Preserving Compression also fits: RAG robustness and adaptive retrieval
  12. BoundaryMORPH: Budgeted Reranking via Active Set Selection for Diffuse Retrieval
All 14
  1. RAILS: Retrieval-Augmented Incremental LLM Clustering at Scale also fits: RAG pipeline design and evaluation
  2. URA-NER: A Unified Retrieval-Augmented Framework with Retrieval Alignment and Uncertainty Reduction for Low-Resource NER
  3. Q-TIE: A Lightweight and Generalizable Re-ranking Framework for Temporal Information Retrieval
  4. Sieve and Sage: Efficient Distraction Filtering for Reliable RALM Abstention also fits: RAG robustness and adaptive retrieval

Foundations

Most cited by papers here

  1. Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks2020cited by 254 here
  2. REALM: Retrieval-Augmented Language Model Pre-Training2020cited by 107 here
  3. Atlas: Few-shot Learning with Retrieval Augmented Language Models2022cited by 82 here
  4. REPLUG: Retrieval-Augmented Black-Box Language Models2023cited by 60 here
  5. In-Context Retrieval-Augmented Language Models2023cited by 49 here

Lineage

The papers this direction builds on, oldest first.

Each paper on the line cites the one before.

  1. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 107 here
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 254 here
  3. 2021End-to-End Training of Multi-Document Reader and Retriever for Open-Domain Question Answeringcited by 15 here
  4. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 82 here
  5. 2022Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLPcited by 16 here
  6. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 60 here
  7. 2023In-Context Retrieval-Augmented Language Modelscited by 49 here
  8. 2023Active Retrieval Augmented Generationcited by 27 here
  9. 2023Making Retrieval-Augmented Language Models Robust to Irrelevant Contextcited by 27 here
  10. 2023RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentationcited by 28 here
  11. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 71 here
  12. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 54 here
  13. 2024Retrieval-Augmented Generation for AI-Generated Content: A Surveycited by 17 here
11 more it builds on, not in this chain
  1. 2022A Survey on Retrieval-Augmented Text Generationcited by 14 here
  2. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 45 here
  3. 2023RA-DIT: Retrieval-Augmented Dual Instruction Tuningcited by 19 here
  4. 2023Learning to Filter Context for Retrieval-Augmented Generationcited by 17 here
  5. 2024RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrievalcited by 12 here
  6. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexitycited by 17 here
  7. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 16 here
  8. 2024xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Tokencited by 26 here
  9. 2024RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMscited by 12 here
  10. 2024CompAct: Compressing Retrieved Documents Actively for Question Answeringcited by 18 here
  11. 2024TurboRAG: Accelerating Retrieval-Augmented Generation with Precomputed KV Caches for Chunked Textcited by 20 here

The 24 most cited of 487.

Browse

30 of 407, ranked 6–35

  1. 6When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories202245
  2. 7RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentation202328
  3. 8Active Retrieval Augmented Generation202327
  4. 9Making Retrieval-Augmented Language Models Robust to Irrelevant Context202327
  5. 10xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token202426
  6. 11TurboRAG: Accelerating Retrieval-Augmented Generation with Precomputed KV Caches for Chunked Text202420
  7. 12RA-DIT: Retrieval-Augmented Dual Instruction Tuning202319
  8. 13CompAct: Compressing Retrieved Documents Actively for Question Answering202418
  9. 14Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLP202216
  10. 15PISCO: Pretty Simple Compression for Retrieval-Augmented Generation202512
All 30
  1. 16RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMs202412
  2. 17Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Models202311
  3. 18Provence: efficient and robust context pruning for retrieval-augmented generation202510
  4. 19Investigating Language Preference of Multilingual RAG Systems202510
  5. 20Accelerating Inference of Retrieval-Augmented Generation via Sparse Context Selection20249
  6. 21Shall We Pretrain Autoregressive Language Models with Retrieval? A Comprehensive Study20239
  7. 22RAGCache: Efficient Knowledge Caching for Retrieval-Augmented Generation20248
  8. 23Context Embeddings for Efficient Answer Generation in RAG20248
  9. 24Don't Do RAG: When Cache-Augmented Generation is All You Need for Knowledge Tasks20248
  10. 25Attention in Large Language Models Yields Efficient Zero-Shot Re-Rankers20247
  11. 26EXIT: Context-Aware Extractive Compression for Enhancing Retrieval-Augmented Generation20247
  12. 27Cache-Craft: Managing Chunk-Caches for Efficient Retrieval-Augmented Generation20256
  13. 28Block-Attention for Efficient Prefilling20246
  14. 29On the Consistency of Multilingual Context Utilization in Retrieval-Augmented Generation20255
  15. 30Multilingual Retrieval-Augmented Generation for Knowledge-Intensive Task20255
  16. 31CacheClip: Accelerating RAG with Effective KV Cache Reuse20255
  17. 32Reliable, Adaptable, and Attributable Language Models with Retrieval20245
  18. 33HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models20245
  19. 34NV-Retriever: Improving text embedding models with effective hard-negative mining20245
  20. 35MemoRAG: Boosting Long Context Processing with Global Memory-Enhanced Retrieval Augmentation20245