TriSum: Learning Summarization Ability from Large Language Models with Structured Rationale

arXiv:2403.10351v1 Announce Type: new
Abstract: The advent of large language models (LLMs) has significantly advanced natural language processing tasks like text summarization. However, their large size and computational demands, coupled with privacy concerns in data transmission, limit their use in resource-constrained and privacy-centric settings. To overcome this, we introduce TriSum, a framework for distilling LLMs' text summarization abilities into a compact, local model. Initially, LLMs extract a set of aspect-triple rationales and summaries, which are refined using a dual-scoring method …

abstract advanced arxiv computational concerns cs.cl data however language language models language processing large language large language models llms natural natural language natural language processing privacy processing summarization tasks text text summarization type