PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
July 9, 20241 citationsOpen Access

MixSumm: Topic-based Data Augmentation using LLMs for Low-resource Extractive Text Summarization

View Full Paper
GSGaurav SahuMahaveer Academy of Technology and Science UniversityILIssam LaradjiServiceNow (United States)

Key Points

Key points are not available for this paper at this time.

Abstract

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.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Sahu et al. (2024) studied this question.

synapsesocial.com/papers/68e60e57b6db6435875a1a90https://doi.org/10.48550/arxiv.2407.07341
Ask AI
Helpful
Bookmark
Share
View Full Paper