# GORAG: Graph-based Online Retrieval Augmented Generation for Dynamic Few-shot Social Media Text Classification

arXiv: https://arxiv.org/abs/2501.02844 · HTML: https://mlsanity.com/paper/2501.02844/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge-graph and structured-knowledge RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 31 of its 83 references that are in the map.
- First posted on arXiv 6 Jan 2025.

## Placed in

- Retrieval-augmented generation / [Knowledge-graph and structured-knowledge RAG](https://mlsanity.com/rag/knowledge-graph-and-structured-knowledge-rag/)

## Builds on (most cited first, 30 of 31)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Deep contextualized word representations](https://mlsanity.com/paper/1802.05365/) (2018)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [Continual Lifelong Learning with Neural Networks: A Review](https://mlsanity.com/paper/1802.07569/) (2018)
- [LIMA: Less Is More for Alignment](https://mlsanity.com/paper/2305.11206/) (2023)
- [RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval](https://mlsanity.com/paper/2401.18059/) (2024)
- [LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression](https://mlsanity.com/paper/2310.06839/) (2023)
- [LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression](https://mlsanity.com/paper/2403.12968/) (2024)
- [Graph Retrieval-Augmented Generation: A Survey](https://mlsanity.com/paper/2408.08921/) (2024)
- [Retrieval-Augmented Generation with Graphs (GraphRAG)](https://mlsanity.com/paper/2501.00309/) (2024)
- [Text Classification Algorithms: A Survey](https://mlsanity.com/paper/1904.08067/) (2019)
- [Recurrent Neural Network for Text Classification with Multi-Task Learning](https://mlsanity.com/paper/1605.05101/) (2016)
- [Bilateral Multi-Perspective Matching for Natural Language Sentences](https://mlsanity.com/paper/1702.03814/) (2017)
- [HDLTex: Hierarchical Deep Learning for Text Classification](https://mlsanity.com/paper/1709.08267/) (2017)
- [Dense X Retrieval: What Retrieval Granularity Should We Use?](https://mlsanity.com/paper/2312.06648/) (2023)
- [A Survey on Text Classification: From Shallow to Deep Learning](https://mlsanity.com/paper/2008.00364/) (2020)
- [Weakly-Supervised Neural Text Classification](https://mlsanity.com/paper/1809.01478/) (2018)
- [CompAct: Compressing Retrieved Documents Actively for Question Answering](https://mlsanity.com/paper/2407.09014/) (2024)
- [On Early Detection of Hallucinations in Factual Question Answering](https://mlsanity.com/paper/2312.14183/) (2023)
- [TopicRNN: A Recurrent Neural Network with Long-Range Semantic Dependency](https://mlsanity.com/paper/1611.01702/) (2016)
- [FoRAG: Factuality-optimized Retrieval Augmented Generation for Web-enhanced Long-form Question Answering](https://mlsanity.com/paper/2406.13779/) (2024)
- [Graph of Records: Boosting Retrieval Augmented Generation for Long-context Summarization with Graphs](https://mlsanity.com/paper/2410.11001/) (2024)
- [Effective Clustering on Large Attributed Bipartite Graphs](https://mlsanity.com/paper/2405.11922/) (2024)
- [Hate Speech Detection with Generalizable Target-aware Fairness](https://mlsanity.com/paper/2406.00046/) (2024)
- [Exposing Cross-Platform Coordinated Inauthentic Activity in the Run-Up to the 2024 U.S. Election](https://mlsanity.com/paper/2410.22716/) (2024)
- [Susceptibility to Unreliable Information Sources: Swift Adoption with Minimal Exposure](https://mlsanity.com/paper/2311.05724/) (2023)
- [TART: Improved Few-shot Text Classification Using Task-Adaptive Reference Transformation](https://mlsanity.com/paper/2306.02175/) (2023)

## Built on by (most cited first, 7 of 7)

- [BookRAG: A Hierarchical Structure-aware Index-based Approach for Retrieval-Augmented Generation on Complex Documents](https://mlsanity.com/paper/2512.03413/) (2025)
- [Survey and Experiments on Mental Disorder Detection via Social Media: From Large Language Models and RAG to Agents](https://mlsanity.com/paper/2504.02800/) (2025)
- [LoopServe: An Adaptive Dual-phase LLM Inference Acceleration System for Multi-Turn Dialogues](https://mlsanity.com/paper/2507.13681/) (2025)
- [ClueAnchor: Clue-Anchored Knowledge Reasoning Exploration and Optimization for Retrieval-Augmented Generation](https://mlsanity.com/paper/2505.24388/) (2025)
- [PolyUQuest: Verifiable Structure-Aware Web RAG over Heterogeneous Graphs](https://mlsanity.com/paper/2607.08269/) (2026)
- [CloSeR: Unified Relational Distillation from Closed-Set Teachers for Category Discovery](https://mlsanity.com/paper/2608.25692/) (2026)
- [Label-Centric Knowledge Retrieval for Zero-Shot Text Classification](https://mlsanity.com/paper/2610.16182/) (2026)

## Abstract (arXiv)

Text classification is vital for Web for Good applications like hate speech and misinformation detection. However, traditional models (e.g., BERT) often fail in dynamic few-shot settings where labeled data are scarce, and target labels frequently evolve. While Large Language Models (LLMs) show promise in few-shot settings, their performance is often hindered by increased input size in dynamic evolving scenarios. To address these issues, we propose GORAG, a Graph-based Online Retrieval-Augmented Generation framework for dynamic few-shot text classification. GORAG constructs and maintains a weighted graph of keywords and text labels, representing their correlations as edges. To model these correlations, GORAG employs an edge weighting mechanism to prioritize the importance and reliability of extracted information and dynamically retrieves relevant context using a tailored minimum-cost spanning tree for each input. Empirical evaluations show GORAG outperforms existing approaches by providing more comprehensive and precise contextual information. Our code is released at: https://github.com/Wyb0627/GORAG.