mlsanityData to 7 Oct 2026

Efficient Context Selection for Long-Context QA: No Tuning, No Iteration, Just Adaptive-k

arXiv 2506.08479 ↗First posted 10 Jun 2025cs.CL cs.AI cs.IRcited by 19

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

Abstract (arXiv)

Retrieval-augmented generation (RAG) and long-context language models (LCLMs) both address context limitations of LLMs in open-domain question answering (QA). However, optimal external context to retrieve remains an open problem: fixing the retrieval size risks either wasting tokens or omitting key evidence. Existing adaptive methods like Self-RAG and Self-Route rely on iterative LLM prompting and perform well on factoid QA, but struggle with aggregation QA, where the optimal context size is both unknown and variable. We present Adaptive-k retrieval, a simple and effective single-pass method that adaptively selects the number of passages based on the distribution of the similarity scores between the query and the candidate passages. It does not require model fine-tuning, extra LLM inferences or changes to existing retriever-reader pipelines. On both factoid and aggregation QA benchmarks, Adaptive-k matches or outperforms fixed-k baselines while using up to 10x fewer tokens than full-context input, yet still retrieves 70% of relevant passages. It improves accuracy across five LCLMs and two embedding models, highlighting that dynamically adjusting context size leads to more efficient and accurate QA.

Key facts. Cited by 19 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 20 of its 26 references that are in the map. First posted on arXiv 10 Jun 2025.

Builds on

20 of 26 references.

Closest ancestors · 5

Same direction, newest first

  1. 2024Long Context vs. RAG for LLMs: An Evaluation and Revisits27 Dec
  2. 2024In Defense of RAG in the Era of Long-Context Language Models3 Sep
  3. 2024RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generation31 Mar
  4. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity21 Mar
  5. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection17 Oct

Other references · 15

  1. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  2. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  3. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
  4. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,203
  5. 2019Universal Adversarial Triggers for Attacking and Analyzing NLPcited by 709
  6. 2023Towards General Text Embeddings with Multi-stage Contrastive Learningcited by 705
  7. 2024∞Bench: Extending Long Context Evaluation Beyond 100K Tokenscited by 360
  8. 2024Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAGcited by 122
  9. 2024HELMET: How to Evaluate Long-Context Language Models Effectively and Thoroughlycited by 119
  10. 2024Retrieval Augmented Generation or Long-Context LLMs? A Comprehensive Study and Hybrid Approachcited by 117
  11. 2024Searching for Best Practices in Retrieval-Augmented Generationcited by 83
  12. 2024Are Long-LLMs A Necessity For Long-Context Tasks?cited by 22
3 more
  1. 2024The Price of Prompting: Profiling Energy Use in Large Language Models Inferencecited by 22
  2. 2024Holistic Reasoning with Long-Context LMs: A Benchmark for Database Operations on Massive Textual Datacited by 11
  3. 2024Retrieval Or Holistic Understanding? Dolce: Differentiate Our Long Context Evaluation Taskscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 4; 2026: 15.

19 papers.

Sort:

By area:

  1. 2026How Many Tools Should an LLM Agent See? A Chance-Corrected Answercited by 7
  2. 2026MemToolAgent: Leveraging Memory for Tool Using Agents Based on Environment and User Feedbackcited by 4
  3. 2025Replace, Don't Expand: Mitigating Context Dilution in Multi-Hop RAG via Fixed-Budget Evidence Assemblycited by 3
  4. 2025Dynamic Context Selection for Retrieval-Augmented Generation: Mitigating Distractors and Positional Biascited by 3
  5. 2026Align Then Adapt: Label-Efficient Adapter Learning for Asymmetric Dense Retrievalcited by 1
  6. 2026MagicSelector: Joint Optimization for Agent Tool Selection via Counterfactual Decomposition and Progressive Rerankingcited by 1
  7. 2026SAGE: SLO-Aware Adaptive Retrieval for Production RAG Systemscited by 1
  8. 2026Noesis: Bidirectional Graph-RAG with Adaptive Parallelism and Cross-Knowledge-Base Semantic Discoverycited by 1
  9. 2026Less can be More: Relieving RAG Bottlenecks via Evidence Frontloading and Pressure-Adaptive Budgetingcited by 1
  10. 2025Beyond RAG vs. Long-Context: Learning Distraction-Aware Retrieval for Efficient Knowledge Groundingcited by 0
  11. 2025Context-Picker: Dynamic context selection using multi-stage reinforcement learningcited by 0
  12. 2026AdaGATE: Adaptive Gap-Aware Token-Efficient Evidence Assembly for Multi-Hop Retrieval-Augmented Generationcited by 0
7 more
  1. 2026GRASP: Graph Agentic Search over Propositions for Multi-hop Question Answeringcited by 0
  2. 2026EASE-TTT: Evidence-Aligned Selective Test-Time Training for Long-Context Question Answeringcited by 0
  3. 2026Tail-Aware Adaptive-k: Query-Adaptive Context Selection for Retrieval-Augmented Generationcited by 0
  4. 2026D2-ScaleAgent: Dual-Dimensional Scaling for Long Document Understandingcited by 0
  5. 2026ViSAR: Training-Free Adaptive-k Retrieval for Visual Document Question Answeringcited by 0
  6. 2026PRAGMA: Evaluating Personalized Guidance with Memory Alignment in Lifelong Conversationscited by 0
  7. 2026BELIEFRAG: Making Adaptive RAG State-Aware under Evolving Evidencecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Leave No Document Behind: Benchmarking Long-Context LLMs with Extended Multi-Doc QA
  2. 2025On the Influence of Context Size and Model Choice in Retrieval-Augmented Generation Systems
  3. 2024RetrievalQA: Assessing Adaptive Retrieval-Augmented Generation for Short-form Open-Domain Question Answering
  4. 2025Improving Context Fidelity via Native Retrieval-Augmented Reasoning
  5. 2025Retrieval Augmented Question Answering: When Should LLMs Admit Ignorance?
  6. 2024Learning When to Retrieve, What to Rewrite, and How to Respond in Conversational QA
  7. 2025Beyond Independent Passages: Adaptive Passage Combination Retrieval for Retrieval Augmented Open-Domain Question Answering
  8. 2024RE-RAG: Improving Open-Domain QA Performance and Interpretability with Relevance Estimator in Retrieval-Augmented Generation