mlsanityData to 7 Oct 2026

Beyond Independent Passages: Adaptive Passage Combination Retrieval for Retrieval Augmented Open-Domain Question Answering

arXiv 2507.04069 ↗First posted 5 Jul 2025cs.CL cs.AI cs.LGcited by 1

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

Abstract (arXiv)

Retrieval-augmented generation (RAG) enhances large language models (LLMs) by incorporating external documents at inference time, enabling up-to-date knowledge access without costly retraining. However, conventional RAG methods retrieve passages independently, often leading to redundant, noisy, or insufficiently diverse context-particularly problematic - particularly problematic in noisy corpora and for multi-hop questions. To address this, we propose Adaptive Passage Combination Retrieval (AdaPCR), a novel framework for open-domain question answering with black-box LMs. AdaPCR explicitly models dependencies between passages by considering passage combinations as units for retrieval and reranking. It consists of a context-aware query reformulation using concatenated passages, and a reranking step trained with a predictive objective aligned with downstream answer likelihood. Crucially, AdaPCR adaptively selects the number of retrieved passages without additional stopping modules. Experiments across several QA benchmarks show that AdaPCR outperforms baselines, particularly in multi-hop reasoning, demonstrating the effectiveness of modeling inter-passage dependencies for improved retrieval.

Key facts. Cited by 1 paper 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 31 of its 53 references that are in the map. First posted on arXiv 5 Jul 2025.

Builds on

31 of 53 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024QPaug: Question and Passage Augmentation for Open-Domain Question Answering of LLMs20 Jun
  2. 2024BlendFilter: Advancing Retrieval-Augmented Large Language Models via Query Generation Blending and Knowledge Filtering16 Feb
  3. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection17 Oct

Other references · 28

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  4. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  5. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  6. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  7. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  8. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,185
  9. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  10. 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,591
  11. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 940
  12. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 911
16 more
  1. 2019Generalization through Memorization: Nearest Neighbor Language Modelscited by 788
  2. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 786
  3. 2023In-Context Retrieval-Augmented Language Modelscited by 694
  4. 2024RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrievalcited by 519
  5. 2023Making Retrieval-Augmented Language Models Robust to Irrelevant Contextcited by 364
  6. 2024The Power of Noise: Redefining Retrieval for RAG Systemscited by 275
  7. 2021RocketQAv2: A Joint Training Method for Dense Passage Retrieval and Passage Re-rankingcited by 175
  8. 2024Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAGcited by 122
  9. 2023Answering Questions by Meta-Reasoning over Multiple Chains of Thoughtcited by 87
  10. 2023Improving Language Models via Plug-and-Play Retrieval Feedbackcited by 87
  11. 2023Search-in-the-Chain: Interactively Enhancing Large Language Models with Search for Knowledge-intensive Taskscited by 73
  12. 2021The Web Is Your Oyster - Knowledge-Intensive NLP against a Very Large Web Corpuscited by 60
  13. 2023Improving Retrieval-Augmented Large Language Models via Data Importance Learningcited by 17
  14. 2018Adaptive Document Retrieval for Deep Question Answeringcited by 16
  15. 2024Tree of Reviews: A Tree-based Dynamic Iterative Retrieval Framework for Multi-hop Question Answeringcited by 4
  16. 2020Diversity Aware Relevance Learning for Argument Searchcited by 3

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Think Before You Retrieve: Learning Test-Time Adaptive Search with Small Language Modelscited by 4

Similar, not cited

Close in wording, no citation either way

  1. 2023Modeling Uncertainty and Using Post-fusion as Fallback Improves Retrieval Augmented Generation with LLMs
  2. 2025Efficient Context Selection for Long-Context QA: No Tuning, No Iteration, Just Adaptive-k
  3. 2024RE-RAG: Improving Open-Domain QA Performance and Interpretability with Relevance Estimator in Retrieval-Augmented Generation
  4. 2024REAR: A Relevance-Aware Retrieval-Augmented Framework for Open-Domain Question Answering
  5. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity
  6. 2025From Retrieval to Generation: Comparing Different Approaches
  7. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering
  8. 2024RetrievalQA: Assessing Adaptive Retrieval-Augmented Generation for Short-form Open-Domain Question Answering