Dynamic Context Selection for Retrieval-Augmented Generation: Mitigating Distractors and Positional Bias
On the map: Retrieval-augmented generation → RAG pipeline design and evaluation
Abstract (arXiv)
Retrieval Augmented Generation (RAG) enhances language model performance by incorporating external knowledge retrieved from large corpora, which makes it highly suitable for tasks such as open domain question answering. Standard RAG systems typically rely on a fixed top k retrieval strategy, which can either miss relevant information or introduce semantically irrelevant passages, known as distractors, that degrade output quality. Additionally, the positioning of retrieved passages within the input context can influence the model attention and generation outcomes. Context placed in the middle tends to be overlooked, which is an issue known as the "lost in the middle" phenomenon. In this work, we systematically analyze the impact of distractors on generation quality, and quantify their effects under varying conditions. We also investigate how the position of relevant passages within the context window affects their influence on generation. Building on these insights, we propose a context-size classifier that dynamically predicts the optimal number of documents to retrieve based on query-specific informational needs. We integrate this approach into a full RAG pipeline, and demonstrate improved performance over fixed k baselines.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Placed in RAG pipeline design and evaluation, one of 15 directions in Retrieval-augmented generation. Builds on 12 of its 13 references that are in the map. First posted on arXiv 16 Dec 2025.
Builds on
12 of 13 references.
Closest ancestors · 3
Same direction, newest first
- 2024Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAG8 Oct
- 2024MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries27 Jan
- 2023Retrieval-Augmented Generation for Large Language Models: A Survey18 Dec
Other references · 9
- 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
- 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
- 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
- 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,259
- 2021MuSiQue: Multihop Questions via Single-hop Question Compositioncited by 893
- 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexitycited by 437
- 2025The Distracting Effect: Understanding Irrelevant Passages in RAGcited by 32
- 2025Efficient Context Selection for Long-Context QA: No Tuning, No Iteration, Just Adaptive-kcited by 19
- 2025DynamicRAG: Leveraging Outputs of Large Language Model as Feedback for Dynamic Reranking in Retrieval-Augmented Generationcited by 14
Built on by
Citing papers per year: 2026: 3.
3 papers.
- 2026Semantically Similar, Logically Distinct: Diagnosing the Semantic-Answerability Gap in Table RAG20 Jul 2026
- 2026How Many Tools Should an LLM Agent See? A Chance-Corrected Answer23 May 2026
- 2026No-Worse Context-Aware Decoding: Preventing Neutral Regression in Context-Conditioned Generation17 Apr 2026
Similar, not cited
Close in wording, no citation either way
- 2025Enhancing Retrieval-Augmented Generation: A Study of Best Practices
- 2024Introducing a new hyper-parameter for RAG: Context Window Utilization
- 2025Grounding Long-Context Reasoning with Contextual Normalization for Retrieval-Augmented Generation
- 2024Contextual Compression in Retrieval-Augmented Generation for Large Language Models: A Survey
- 2025A Survey on Knowledge-Oriented Retrieval-Augmented Generation
- 2024Context Awareness Gate For Retrieval Augmented Generation
- 2025Oreo: A Plug-in Context Reconstructor to Enhance Retrieval-Augmented Generation
- 2025On the Influence of Context Size and Model Choice in Retrieval-Augmented Generation Systems