MixSumm: Topic-based Data Augmentation using LLMs for Low-resource Extractive Text Summarization
Sahu, Gaurav, Laradji, Issam H.
–arXiv.org Artificial Intelligence
Low-resource extractive text summarization is a vital but heavily underexplored area of research. Prior literature either focuses on abstractive text summarization or prompts a large language model (LLM) like GPT-3 directly to generate summaries. In this work, we propose MixSumm for low-resource extractive text summarization. Specifically, MixSumm prompts an open-source LLM, LLaMA-3-70b, to generate documents that mix information from multiple topics as opposed to generating documents without mixup, and then trains a summarization model on the generated dataset. We use ROUGE scores and L-Eval, a reference-free LLaMA-3-based evaluation method to measure the quality of generated summaries. We conduct extensive experiments on a challenging text summarization benchmark comprising the TweetSumm, WikiHow, and ArXiv/PubMed datasets and show that our LLM-based data augmentation framework outperforms recent prompt-based approaches for low-resource extractive summarization. Additionally, our results also demonstrate effective knowledge distillation from LLaMA-3-70b to a small BERT-based extractive summarizer.
arXiv.org Artificial Intelligence
Jul-9-2024
- Country:
- North America
- Dominican Republic (0.04)
- United States > Louisiana
- Orleans Parish > New Orleans (0.04)
- Mexico > Mexico City
- Mexico City (0.04)
- Canada
- British Columbia (0.04)
- Ontario
- Waterloo Region > Waterloo (0.04)
- Toronto (0.04)
- Europe
- Spain > Catalonia
- Barcelona Province > Barcelona (0.04)
- Ireland > Leinster
- County Dublin > Dublin (0.04)
- Spain > Catalonia
- Asia
- Singapore (0.04)
- China > Hong Kong (0.04)
- Middle East > UAE
- Abu Dhabi Emirate > Abu Dhabi (0.04)
- North America
- Genre:
- Research Report > New Finding (0.66)
- Technology: