mlsanityData to 7 Oct 2026

Retrieval-Augmented Classification with Decoupled Representation

arXiv 2303.13065 ↗First posted 23 Mar 2023cs.CLcited by 0

On the map: Retrieval-augmented generation → Generation and context integration

Abstract (arXiv)

Retrieval augmented methods have shown promising results in various classification tasks. However, existing methods focus on retrieving extra context to enrich the input, which is noise sensitive and non-expandable. In this paper, following this line, we propose a k-nearest-neighbor (KNN) -based method for retrieval augmented classifications, which interpolates the predicted label distribution with retrieved instances' label distributions. Different from the standard KNN process, we propose a decoupling mechanism as we find that shared representation for classification and retrieval hurts performance and leads to training instability. We evaluate our method on a wide range of classification datasets. Experimental results demonstrate the effectiveness and robustness of our proposed method. We also conduct extra experiments to analyze the contributions of different components in our model.footnoteurlhttps://github.com/xnliang98/knn-cls-w-decoupling

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Generation and context integration, one of 15 directions in Retrieval-augmented generation. Builds on 14 of its 19 references that are in the map. First posted on arXiv 23 Mar 2023.

Builds on

14 of 19 references.

References · 14

  1. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  2. 2017A Broad-Coverage Challenge Corpus for Sentence Understanding through Inferencecited by 2,665
  3. 2017Billion-scale similarity search with GPUscited by 2,477
  4. 2019Generalization through Memorization: Nearest Neighbor Language Modelscited by 788
  5. 2020Revisiting Pre-Trained Models for Chinese Natural Language Processingcited by 262
  6. 2020Nearest Neighbor Machine Translationcited by 209
  7. 2020Generation-Augmented Retrieval for Open-domain Question Answeringcited by 186
  8. 2022ReACC: A Retrieval-Augmented Code Completion Frameworkcited by 117
  9. 2020OCNLI: Original Chinese Natural Language Inferencecited by 86
  10. 2022Training Data is More Valuable than You Think: A Simple and Effective Method by Retrieving from Training Datacited by 61
  11. 2021Adaptive Nearest Neighbor Machine Translationcited by 58
  12. 2021Controllable Semantic Parsing via Retrieval Augmentationcited by 35
2 more
  1. 2021Cross-Modal Retrieval Augmentation for Multi-Modal Classificationcited by 20
  2. 2020Neural Retrieval for Question Answering with Cross-Attention Supervised Data Augmentationcited by 18

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023Retrieval-augmented Multi-label Text Classification
  2. 2024A Statistical Framework for Data-dependent Retrieval-Augmented Models
  3. 2025Automatic Labelling with Open-source LLMs using Dynamic Label Schema Integration
  4. 2023RAHNet: Retrieval Augmented Hybrid Network for Long-tailed Graph Classification
  5. 2024NUDGE: Lightweight Non-Parametric Fine-Tuning of Embeddings for Retrieval
  6. 2022kNN-NER: Named Entity Recognition with Nearest Neighbor Search
  7. 2023Retrieval-Augmented Meta Learning for Low-Resource Text Classification
  8. 2022kNN-Prompt: Nearest Neighbor Zero-Shot Inference