arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.04855cs.CLcs.AI
收藏

提升抽取式摘要连贯性:数据集与基于大语言模型的实验

Towards Enhancing Coherence in Extractive Summarization: Dataset and Experiments with LLMs

Adobe Research(奥多比研究院);Arizona State University(亚利桑那州立大学)

Mihir Parmar, Hanieh Deilamsalehy, Franck Dernoncourt, Seunghyun Yoon, Ryan A. Rossi, Trung Bui

AI总结:

本文针对大语言模型抽取式摘要不连贯问题,提出融合用户意图的人工标注数据集,并通过监督微调与人类反馈对齐LLM,使Falcon-40B和Llama-2-13B的Rouge-L提升约10%。

摘要:

抽取式摘要在自然语言处理中扮演着关键角色,因为它能够高效地总结多样化的内容,同时忠实于原始内容。尽管大语言模型(LLMs)在抽取式摘要方面取得了显著进展,但这些摘要经常表现出不连贯性。连贯摘要的一个重要方面是其对目标用户的可读性。尽管已经提出了许多用于生成连贯抽取式摘要的数据集和基准,但目前没有一个数据集或基准将用户意图纳入其中以改进抽取式摘要的连贯性。受此启发,我们提出了一个系统构建的人工标注数据集,该数据集由五个公开数据集的连贯摘要和自然语言用户反馈组成,为如何改进抽取式摘要的连贯性提供了有价值的见解。我们利用该数据集通过监督微调与自然语言人类反馈来对齐大语言模型,以增强其生成摘要的连贯性。使用Falcon-40B和Llama-2-13B进行的初步实验表明,在生成连贯摘要方面性能显著提升(Rouge-L约提高10%)。我们进一步利用人类反馈对FLAN-T5等指令微调模型进行基准测试,得出了若干有趣的发现。数据和源代码可在https://github.com/Mihir3009/Extract-AI获取。

英文摘要:

Extractive summarization plays a pivotal role in natural language processing due to its wide-range applications in summarizing diverse content efficiently, while also being faithful to the original content. Despite significant advancement achieved in extractive summarization by Large Language Models (LLMs), these summaries frequently exhibit incoherence. An important aspect of the coherent summary is its readability for intended users. Although there have been many datasets and benchmarks proposed for creating coherent extractive summaries, none of them currently incorporate user intent to improve coherence in extractive summarization. Motivated by this, we propose a systematically created human-annotated dataset consisting of coherent summaries for five publicly available datasets and natural language user feedback, offering valuable insights into how to improve coherence in extractive summaries. We utilize this dataset for aligning LLMs through supervised fine-tuning with natural language human feedback to enhance the coherence of their generated summaries. Preliminary experiments with Falcon-40B and Llama-2-13B show significant performance improvements (~10% Rouge-L) in terms of producing coherent summaries. We further utilize human feedback to benchmark results over instruction-tuned models such as FLAN-T5 which resulted in several interesting findings. Data and source code are available at https://github.com/Mihir3009/Extract-AI.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑