Summary of Clustering Algorithms and Rag Enhancing Semi-supervised Text Classification with Large Llms, by Shan Zhong et al.
Clustering Algorithms and RAG Enhancing Semi-Supervised Text Classification with Large LLMs
by Shan Zhong, Jiahao Zeng, Yongxin Yu, Bohong Lin
First submitted to arxiv on: 9 Nov 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed Clustering, Labeling, then Augmenting framework improves performance in Semi-Supervised Text Classification (SSTC) by effectively utilizing vast datasets with limited labeled examples. The framework employs clustering to select representative “landmarks” for labeling and uses an ensemble of augmentation techniques including Retrieval-Augmented Generation (RAG), Large Language Model (LLMs)-based rewriting, and synonym substitution to generate synthetic labeled data. State-of-the-art accuracies are achieved on the Reuters dataset (95.41%) and Web of Science dataset (82.43%). The approach reduces reliance on human labeling efforts and ensures high data quality while minimizing privacy risks. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper creates a new way to classify text without needing lots of labeled examples. It’s like finding important points in a big map, then using those points as helpers to create more fake labeled data. This helps computers learn faster and better from limited labeled information. The results show this method is the best for certain kinds of text classification tasks. |
Keywords
» Artificial intelligence » Clustering » Large language model » Rag » Retrieval augmented generation » Semi supervised » Text classification
