Retrieval-Augmented Classification

Follow this topic Ask about this topic

Retrieval-augmented classification studies how models can use stored examples, prototypes, label definitions, or domain rules when assigning categories. Common approaches include nearest-neighbor and prototype methods, retrieval-augmented language models, and cascades that retrieve candidates before a classifier verifies them; some also adapt thresholds or search hierarchies. These methods can help with rare classes, large label sets, changing data, and settings where predictions must stay within an approved taxonomy, while reducing the need to retrain models. A central challenge is retrieving evidence that is both relevant and discriminative: similarity alone may not resolve confusable labels, and systems must balance accuracy with context limits, cost, robustness, and reliable abstention.

Latest papers

35 papers9 papers in the last four weeks, against 2 the four weeks before. 0.1% of all new papers.

From Noisy Retrieval to Decision Evidence: Silver Evidence Demonstrations for In-Context Learning
Oct 23, 2026Masoud Monajatipoor, Fazlolah Mohaghegh, Hamid Reza Hassanzadeh +2Retrieval-Augmented ICL In-Context Learning
Optum AI
ReCoG: Relational Concept Graph for Training-Free Personalization
Oct 22, 2026Changseon Yu, Hyeokjun KweonRetrieval-Augmented Classification VLM Reasoning
GSAIM, Chung-Ang University
Beyond the Vote: When Do LLMs Add Value to Retrieval-Based Tabular Classification?
Oct 21, 2026Ziquan Wang, Yuxuan Nie, Jian Ma +1Tabular ICL Retrieval-Augmented ICL
Hangzhou International Innovation Institute, Beihang University, Hangzhou, China · Peking University, Beijing, China
EpiLens: Lightweight RAG for Epidemiological Knowledge Acquisition
Oct 19, 2026Vincenzo Perri, Ciro Cattuto, Daniela PaolottiLLM Information Extraction Evidence Selection
ISI Foundation, Turin, Italy.
From Retrieval to Recognition:Knowledge-Enhanced Post-training of Time Series Foundation Models for Classification
Oct 19, 2026Zhen Liu, Yucheng Wang, Yingpeng Du +5Time Series Classification Time-Series Foundation Models
Nanyang Technological University, Singapore · Institute of Advanced Intelligence and Computing (IAIC), A*STAR, Singapore · AI Center of Excellence for Manufacturing (AIMfg), A*STAR, Singapore +2
Label-Centric Knowledge Retrieval for Zero-Shot Text Classification
Oct 12, 2026Daoping Wu, Dong Wang, Siyu Liu +5Zero-Shot Text Classification Large Language Model-Based Text Classification
Zhejiang Lab, Hangzhou, China · School of Computer Science and Software Engineering, Harbin Institute of Technology, China · School of Mechanical Engineering, Shanghai Jiao Tong University, China
RSAJEV: Training-Free Abstaining Prototype Memory for Eliminating Silent Hallucination in JEV-Based Remote Sensing Classification
Oct 11, 2026Man Chen, Antai Chen, Shuai Xu +5Remote Sensing Scene Classification VLM Hallucination Mitigation
School of Computer Science and Engineering, Anhui University of Science and Technology, Huainan 232001, Anhui, China, and also with the School of Electrical Automation and Information Engineering, Tianjin University, Tianjin 300072, China, and the State Key Laboratory of Digital Intelligent Technology for Unmanned Coal Mining, Huainan 232001, Anhui, China · School of Computer Science and Engineering, Anhui University of Science and Technology, Huainan 232001, Anhui, China · School of Computer Science and Engineering, Anhui University of Science and Technology, Huainan 232001, Anhui, China, and also with the State Key Laboratory of Digital Intelligent Technology for Unmanned Coal Mining, Huainan 232001, Anhui, China +1
OntoAR-HAR: Ontology-Guided Agentic RAG with Personalized Memory for Human Activity Recognition
Oct 11, 2026Xiangqing Lu, Tao Zhu, Liang Yu +6Human Activity Recognition Retrieval-Augmented Classification
School of Computer Science, University of South China, Hengyang, China · School of Computer Science and Technology, Dalian University of Technology, Dalian, China · Hunan University, Changsha, China +1
Revitalizing Medical Time Series with Vision-Informed Retrieval: A Vision-Language Perspective
Sep 28, 2026Guoqi Yu, Juncheng Wang, Shujun WangMultivariate Time Series Classification Time Series Classification
Department of Biomedical Engineering and Sports Technology The Hong Kong Polytechnic University
TRACE: Deployable Tree-Relational Structure Enhancement for Oncology LLMs
Sep 20, 2026Jizheng Lai, Yingyun Li, Ying Qin +1Medical LLMs LLM Grounding
Pharmaron, China · AI Starfish, China
From Confusion to Clarity: Confusion-Aware Retrieval and Knowledge Injection for Text Classification
Sep 1, 2026Manish Gupta, Chaitanya Giri, Jayasimha TalurZero-Shot Text Classification Retrieval-Augmented Classification
Amazon
Retrieval-Augmented Classification of Environmental Mitigations in Hydropower Licensing Documents
Aug 24, 2026Hong-Jun Yoon, Tom Ruggles, Joanna Lee +1Retrieval-Augmented Classification Multi-Label Classification
Computational Sciences and Engineering Division, Oak Ridge National Laboratory, Oak Ridge, Tennessee 37830, USA · Environmental Sciences Division, Oak Ridge National Laboratory, Oak Ridge, Tennessee 37830, USA · Farragut High School, Knoxville, Tennessee 37934
HIRA: A Human-in-the-Loop Retrieval-Augmented Cascade for Document Classification in Regulated Industries
Aug 22, 2026Shangxuan Tian, Yanhui Chen, Carlos QueirozText Classification Retrieval-Augmented Classification
Standard Chartered Bank Guangzhou, China · OCBC Singapore
Retrieving Relations, Detecting Fallacies: A RAG Approach to Political Debate Analysis
Aug 18, 2026Deborah Dore, Greta Damo, Elena Cabrio +1Computational Argumentation Political Discourse Analysis
Université Côte d’Azur, CNRS, INRIA, I3S, France
Retrieval-Augmented Vision Foundation Models for Robust Leukemia Cell Classification across Multiple Microscopy Datasets
Aug 11, 2026Carlos Zamora, Hiram Zuniga, Ulises Orozco-Rosas +1Retrieval-Augmented Classification Vision Foundation Model Adaptation
CETYS Universidad, Ave. CETYS Universidad No. 4, Fracc. El Lago, C.P. 22210, Tijuana, Baja California, Mexico
Defending Retrieval-Augmented Intrusion Detection Against Knowledge Poisoning and Prompt Injection
Aug 8, 2026Kaysarul Anas Apurba, Md. Hasibul Hasan, Mahedee Zaman Moon +2Retrieval-Augmented Classification RAG Poisoning Attacks
Laurentian University Ontario, Canada · Centennial College Ontario, Canada · The University of Osaka Osaka, Japan
PaperRouter-Agent: A Content-Grounded LLM Agent for Personalized Hierarchical Paper Routing
Jul 13, 2026Keshen Zhou, Lintao Wang, Suqin Yuan +3LLM Personalization Retrieval-Augmented Classification
University of Sydney, Sydney, NSW 2006, Australia
Constraint-Aware Hierarchical Search for Regulation-Driven Fine-Grained Classification
Jul 12, 2026Siyu Wang, Wei Tan, Lulu ChenHierarchical Classification Retrieval-Augmented Classification
aGusu Laboratory of Materials, Suzhou, China · cSuzhou Digital China Wuxin Intelligent Technology Co., Ltd., Suzhou, China
When Retrieval Metrics Mislead: Measuring Policy Signal in Long-Horizon Tool-Use Agents
Jun 22, 2026Tianyu Ding, Juan Pablo De la Cruz WeinsteinTool-Use Evaluation Retrieval-Augmented Classification
Amazon Web Services
Cross-lingual Retrieval-Augmented Classification for Dysarthria Severity Assessment
Jun 22, 2026Taeyoung Jeong, Insung Lee, Du-Seong Chang +1Retrieval-Augmented Classification Speech Quality Assessment
Department of Artificial Intelligence, Sogang University, South Korea
Retrieval-Based Multi-Label Legal Annotation: Extensible, Data-Efficient and Hallucination-Free
May 16, 2026Li Zhang, Jaromir Savelka, Kevin AshleyLegal NLP Multi-Label Classification
University of Pittsburgh, Pittsburgh, PA, USA · Carnegie Mellon University, Pittsburgh, PA, USA
RAPT: Retrieval-Augmented Post-hoc Thresholding for Multi-Label Classification
May 15, 2026Lasal Jayawardena, Nirmalie Wiratunga, Ikechukwu Nkisi-Orji +1Document Understanding Multi-Label Classification
Robert Gordon University, Aberdeen, United Kingdom · William Nicol (Aberdeen) Limited, Aberdeen, United Kingdom
DeepTaxon: An Interpretable Retrieval-Augmented Multimodal Framework for Unified Species Identification and Discovery
Apr 27, 2026Jiawei Wang, Ming Lei, Yaning Yang +8Retrieval-Augmented Classification AI-Assisted Scientific Research
National University of Singapore · Hunan University · Xiangtan University +4
Knowledge-driven Augmentation and Retrieval for Integrative Temporal Adaptation
Apr 23, 2026Weisi Liu, Guangzeng Han, Xiaolei HuangDomain Adaptation Retrieval-Augmented Classification
University of Memphis
T-DuMpRa: Teacher-guided Dual-path Multi-prototype Retrieval Augmented framework for fine-grained medical image classification
Apr 19, 2026Zixuan Tang, Shen ZhaoPrototype-Based Classification Retrieval-Augmented Classification
School of Intelligent Systems Engineering, Sun Yat-sen University, Shenzhen, China
Retrieve, Then Classify: Corpus-Grounded Automation of Clinical Value Set Authoring
Apr 16, 2026Sumit Mukherjee, Juan Shu, Nairwita Mazumder +4Healthcare Retrieval-Augmented Classification
Oracle Health Data Intelligence
Retrieval Augmented Classification for Confidential Documents
Apr 9, 2026Yeseul E. Chang, Rahul Kailasa, Simon Shim +2Retrieval-Augmented Classification Text Classification
Department of Security Convergence, Chung-Ang University, Seoul, South Korea · Department of Applied Data Science, San Jose State University, San Jose, CA, United States · Department of Industrial Security, Chung-Ang University, Seoul, South Korea
Learning to Query History: Nonstationary Classification via Learned Retrieval
Apr 8, 2026Jimmy Gammell, Bishal Thapaliya, Yoon Jung +3Classification Retrieval-Augmented Classification
Purdue University, Elmore Family School of Electrical and Computer Engineering. · Amazon. · Georgia Institute of Technology.
BiMind: A Dual-Head Reasoning Model with Attention-Geometry Adapter for Incorrect Information Detection
Apr 7, 2026Zhongxing Zhang, Emily K. Vraga, Jisu Huh +1Fake News Detection Retrieval-Augmented Classification
University of Minnesota, Twin Cities
MA-IDS: Multi-Agent RAG Framework for IoT Network Intrusion Detection with an Experience Library
Apr 7, 2026Md Shamimul Islam, Luis G. Jaimes, Ayesha S. DinaExplainable Intrusion Detection IoT Intrusion Detection
Department of Computer Science, Florida Polytechnic University, Lakeland, Florida

Oct 23, 2026J/K move · Enter open · S save

From Noisy Retrieval to Decision Evidence: Silver Evidence Demonstrations for In-Context Learning

Masoud Monajatipoor, Fazlolah Mohaghegh, Hamid Reza Hassanzadeh, Akash Uttamrao Bhoite+1

Optum AI

Retrieval-Augmented ICL In-Context Learning Retrieval-Augmented Classification RAG Robustness

Open paper AskPDF arXiv

RAG and retrieval-augmented few-shot ICL can struggle when decision-relevant evidence is buried in long, noisy context. Retrieved passages and demonstrations may contain redundant or distracting information. Although expert-labeled development examples may identify the text supporting each decision, these annotations are typically used only as answer-side rationales rather than as supervision for filtering noisy retrieval. We propose silver-evidence demonstrations, which replace raw retrieved passages in ICL examples with generated, target-conditioned evidence summaries. For each labeled development example, an LLM generates silver evidence without access to the expert label or gold evidence; this evidence is then paired with the expert label and gold evidence where available. At test time, a single structured call generates silver evidence from retrieved passages and then predicts the final label and decision evidence. Across EI 2.0, SciFact, synthetic policy retrieval, and HICRIC/IMR data, our full method improves over equally sized gold-only ICL (label-only for policy) on three of four datasets and improves evidence F1 on all annotated datasets. It also achieves higher mean label accuracy than InstructRAG-style ICL on all four datasets. These results suggest that replacing demonstration-side retrieved passages with compact, target-conditioned silver evidence is particularly useful for decisions based on long and noisy text, where it reduces distracting context while preserving decision-relevant signals and expert supervision.