mlsanityData to 14 Oct 2026

Multi-Field Adaptive Retrieval

arXiv 2410.20056 ↗First posted 26 Oct 2024cs.IR cs.CLcited by 4

On the map: Retrieval-augmented generation → RAG pipeline design and evaluation

Abstract (arXiv)

Document retrieval for tasks such as search and retrieval-augmented generation typically involves datasets that are unstructured: free-form text without explicit internal structure in each document. However, documents can have a structured form, consisting of fields such as an article title, message body, or HTML header. To address this gap, we introduce Multi-Field Adaptive Retrieval (MFAR), a flexible framework that accommodates any number of and any type of document indices on structured data. Our framework consists of two main steps: (1) the decomposition of an existing document into fields, each indexed independently through dense and lexical methods, and (2) learning a model which adaptively predicts the importance of a field by conditioning on the document query, allowing on-the-fly weighting of the most likely field(s). We find that our approach allows for the optimized use of dense versus lexical representations across field types, significantly improves in document ranking over a number of existing retrievers, and achieves state-of-the-art performance for multi-field structured data.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Placed in RAG pipeline design and evaluation, one of 15 directions in Retrieval-augmented generation. Builds on 36 of its 49 references that are in the map. First posted on arXiv 26 Oct 2024.

Builds on

36 of 49 references.

References · 36

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  3. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  4. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  5. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  6. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,163
  7. 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,605
  8. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,216
  9. 2015Image-based Recommendations on Styles and Substitutescited by 706
  10. 2019Latent Retrieval for Weakly Supervised Open Domain Question Answeringcited by 695
  11. 2019CodeSearchNet Challenge: Evaluating the State of Semantic Code Searchcited by 654
  12. 2016Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filteringcited by 520
24 more
  1. 2015Compositional Semantic Parsing on Semi-Structured Tablescited by 515
  2. 2021Large Dual Encoders Are Generalizable Retrieverscited by 456
  3. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexitycited by 451
  4. 2017Efficient Natural Language Response Suggestion for Smart Replycited by 229
  5. 2024BM25S: Orders of magnitude faster lexical search via eager sparse scoringcited by 88
  6. 2021Open Domain Question Answering over Tables via Dense Retrievalcited by 74
  7. 2024AvaTaR: Optimizing LLM Agents for Tool Usage via Contrastive Reasoningcited by 72
  8. 2022Shopping Queries Dataset: A Large-Scale ESCI Benchmark for Improving Product Searchcited by 65
  9. 2019Answering Complex Open-domain Questions Through Iterative Query Generationcited by 60
  10. 2021Salient Phrase Aware Dense Retrieval: Can a Dense Retriever Imitate a Sparse One?cited by 60
  11. 2019Improving Multilingual Sentence Embedding using Bi-directional Dual Encoder with Additive Margin Softmaxcited by 58
  12. 2024Instruction-tuned Language Models are Better Knowledge Learnerscited by 55
  13. 2024STaRK: Benchmarking LLM Retrieval on Textual and Relational Knowledge Basescited by 55
  14. 2020Leveraging Semantic and Lexical Matching to Improve the Recall of Document Retrieval Systems: A Hybrid Approachcited by 32
  15. 2023Decomposing Complex Queries for Tip-of-the-tongue Retrievalcited by 24
  16. 2023Structure-Aware Language Model Pretraining Improves Dense Retrieval on Structured Datacited by 23
  17. 2020Table Search Using a Deep Contextualized Language Modelcited by 22
  18. 2022UnifieR: A Unified Retriever for Large-Scale Retrievalcited by 19
  19. 2023Overview of BioASQ 2023: The eleventh BioASQ challenge on Large-Scale Biomedical Semantic Indexing and Question Answeringcited by 18
  20. 2023Wikiformer: Pre-training with Structured Information of Wikipedia for Ad-hoc Retrievalcited by 15
  21. 2022Table Retrieval May Not Necessitate Table-specific Model Designcited by 11
  22. 2022A Dense Representation Framework for Lexical and Semantic Matchingcited by 8
  23. 2017Neural Ranking Models with Multiple Document Fieldscited by 7
  24. 2021Semantic Table Retrieval using Keyword and Table Queriescited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 2.

4 papers.

  1. 2026Field-Aware Agent Skill Retrievalcited by 4
  2. 2025Autofocus Retrieval: An Effective Pipeline for Multi-Hop Question Answering With Semi-Structured Knowledgecited by 3
  3. 2025PaperRegister: Boosting Flexible-grained Paper Search via Hierarchical Register Indexingcited by 1
  4. 2026Co-adaptive Rule Routing and Constraining for Structured Knowledge Retrievalcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025REAL-MM-RAG: A Real-World Multi-Modal Retrieval Benchmark
  2. 2025Cluster-based Adaptive Retrieval: Dynamic Context Selection for RAG Applications
  3. 2026From BM25 to Corrective RAG: Benchmarking Retrieval Strategies for Text-and-Table Documents
  4. 2025MacRAG: Compress, Slice, and Scale-up for Multi-Scale Adaptive Context RAG
  5. 2026CHOP: Chunkwise Context-Preserving Framework for RAG on Multi Documents
  6. 2024UDA: A Benchmark Suite for Retrieval Augmented Generation in Real-world Document Analysis
  7. 2026Adaptive Chunking: Optimizing Chunking-Method Selection for RAG
  8. 2025Are We on the Right Way for Assessing Document Retrieval-Augmented Generation?