GORAG: Graph-based Online Retrieval Augmented Generation for Dynamic Few-shot Social Media Text Classification
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866918312099708928 |
|---|---|
| author | Wang, Yubo Li, Haoyang Teng, Fei Chen, Lei |
| author_facet | Wang, Yubo Li, Haoyang Teng, Fei Chen, Lei |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_02844 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GORAG: Graph-based Online Retrieval Augmented Generation for Dynamic Few-shot Social Media Text Classification Wang, Yubo Li, Haoyang Teng, Fei Chen, Lei Computation and Language Information Retrieval Machine Learning 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. |
| title | GORAG: Graph-based Online Retrieval Augmented Generation for Dynamic Few-shot Social Media Text Classification |
| topic | Computation and Language Information Retrieval Machine Learning |
| url | https://arxiv.org/abs/2501.02844 |