Saved in:
Bibliographic Details
Main Authors: Tong, Xindi, Zhu, Yujin, Fan, Shijian, Xu, Liang
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2409.17640
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909463598858240
author Tong, Xindi
Zhu, Yujin
Fan, Shijian
Xu, Liang
author_facet Tong, Xindi
Zhu, Yujin
Fan, Shijian
Xu, Liang
contents Long text summarization, gradually being essential for efficiently processing large volumes of information, stays challenging for Large Language Models (LLMs) such as GPT and LLaMA families because of the insufficient open-sourced training datasets and the high requirement of contextual details dealing. To address the issue, we design a novel zero-shot transfer learning framework, abbreviated as T3, to iteratively training a baseline LLM on an assistant task for the target task, where the former should own richer data resources and share structural or semantic similarity with the latter. In practice, T3 is approached to deal with the long text summarization task by utilizing question answering as the assistant task, and further validated its effectiveness on the BBC summary, NarraSum, FairytaleQA, and NLQuAD datasets, with up to nearly 14% improvement in ROUGE, 35% improvement in BLEU, and 16% improvement in Factscore compared to three baseline LLMs, demonstrating its potential for more assistant-target task combinations.
format Preprint
id arxiv_https___arxiv_org_abs_2409_17640
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle T3: A Novel Zero-shot Transfer Learning Framework Iteratively Training on an Assistant Task for a Target Task
Tong, Xindi
Zhu, Yujin
Fan, Shijian
Xu, Liang
Computation and Language
Artificial Intelligence
Long text summarization, gradually being essential for efficiently processing large volumes of information, stays challenging for Large Language Models (LLMs) such as GPT and LLaMA families because of the insufficient open-sourced training datasets and the high requirement of contextual details dealing. To address the issue, we design a novel zero-shot transfer learning framework, abbreviated as T3, to iteratively training a baseline LLM on an assistant task for the target task, where the former should own richer data resources and share structural or semantic similarity with the latter. In practice, T3 is approached to deal with the long text summarization task by utilizing question answering as the assistant task, and further validated its effectiveness on the BBC summary, NarraSum, FairytaleQA, and NLQuAD datasets, with up to nearly 14% improvement in ROUGE, 35% improvement in BLEU, and 16% improvement in Factscore compared to three baseline LLMs, demonstrating its potential for more assistant-target task combinations.
title T3: A Novel Zero-shot Transfer Learning Framework Iteratively Training on an Assistant Task for a Target Task
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2409.17640