# Generation and context integration

Area: [Retrieval-augmented generation](https://mlsanity.com/rag/index.md). HTML: https://mlsanity.com/rag/generation-and-context-integration/

## Key facts

- Generation and context integration: 407 papers on arXiv since 2020 (data through 14 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).
- 16 new papers 17 Sep–14 Oct.

## Most cited here

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020), cited by 254 papers here
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020), cited by 107 papers here
- [Atlas: Few-shot Learning with Retrieval Augmented Language Models](https://mlsanity.com/paper/2208.03299/) (2022), cited by 82 papers here
- [REPLUG: Retrieval-Augmented Black-Box Language Models](https://mlsanity.com/paper/2301.12652/) (2023), cited by 60 papers here
- [In-Context Retrieval-Augmented Language Models](https://mlsanity.com/paper/2302.00083/) (2023), cited by 49 papers here
- [When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories](https://mlsanity.com/paper/2212.10511/) (2022), cited by 45 papers here
- [RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentation](https://mlsanity.com/paper/2310.04408/) (2023), cited by 28 papers here
- [Active Retrieval Augmented Generation](https://mlsanity.com/paper/2305.06983/) (2023), cited by 27 papers here
- [Making Retrieval-Augmented Language Models Robust to Irrelevant Context](https://mlsanity.com/paper/2310.01558/) (2023), cited by 27 papers here
- [xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token](https://mlsanity.com/paper/2405.13792/) (2024), cited by 26 papers here

## New (17 Sep–14 Oct)

- [SAFE-KV: Causal Suffix Repair for Behavior-Preserving Non-Prefix KV Cache Reuse in RAG](https://mlsanity.com/paper/2610.15186/) (2026-10-10)
- [SignRAG: Unified Retrieval-Augmented Gloss-Free Sign Language Translation](https://mlsanity.com/paper/2610.11371/) (2026-10-08)
- [Does Document Structure Help Dense Retrieval? A Placebo-Controlled Ablation of Four Mechanisms Across Two Corpora](https://mlsanity.com/paper/2610.10170/) (2026-10-07)
- [EntroPrefill: Renyi-Guided Context Pruning with Conditional Stability Guarantees for Retrieval-Augmented Generation](https://mlsanity.com/paper/2610.09757/) (2026-10-07)
- [UNREAL: Unifying Retrieval and Long-Context with a Single Model](https://mlsanity.com/paper/2610.08463/) (2026-10-06)
- [Principled Top-k Selection for Language Models with Hybrid Gradients](https://mlsanity.com/paper/2610.04162/) (2026-10-03)
- [CacheRepair: Learning to Repair Cross-Chunk Context in RAG for KV Cache Fusion](https://mlsanity.com/paper/2609.35139/) (2026-09-28)
- [RelaxKV: Recomputation Guided by the Query with Sparse Context Attention for Efficient KV Cache Reuse](https://mlsanity.com/paper/2609.33503/) (2026-09-27)
- [When Does Dense Retrieval Need Asymmetric Geometry? A Bias-Variance Theory of Shared and Dual Projections](https://mlsanity.com/paper/2609.32488/) (2026-09-26)
- [Beyond the Context Window: An Adaptive Entropy-Based Routing Framework for Hybrid Retrieval and Long-Context Language Models](https://mlsanity.com/paper/2609.35831/) (2026-09-23)
- [MORSE: Multi-Context Ordering via Reverse Scoring for Evidence-Preserving Compression](https://mlsanity.com/paper/2609.27380/) (2026-09-23)
- [BoundaryMORPH: Budgeted Reranking via Active Set Selection for Diffuse Retrieval](https://mlsanity.com/paper/2609.27213/) (2026-09-23)
- [RAILS: Retrieval-Augmented Incremental LLM Clustering at Scale](https://mlsanity.com/paper/2609.24464/) (2026-09-21)
- [URA-NER: A Unified Retrieval-Augmented Framework with Retrieval Alignment and Uncertainty Reduction for Low-Resource NER](https://mlsanity.com/paper/2609.24372/) (2026-09-21)
- [Q-TIE: A Lightweight and Generalizable Re-ranking Framework for Temporal Information Retrieval](https://mlsanity.com/paper/2609.23880/) (2026-09-20)
- [Sieve and Sage: Efficient Distraction Filtering for Reliable RALM Abstention](https://mlsanity.com/paper/2609.35794/) (2026-09-17)