arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2405.04039cs.CLcs.AIcs.LG
收藏

利用GPT增强文本摘要:一种最小化幻觉的策略

Utilizing GPT to Enhance Text Summarization: A Strategy to Minimize Hallucinations

University of Colorado - Colorado Springs(科罗拉多大学科罗拉多斯普林斯分校);DataCrunch Lab, LLC(DataCrunch实验室有限责任公司);North Carolina State University(北卡罗来纳州立大学)

Hassan Shakil, Zeydy Ortiz, Grant C. Forbes

AI总结:

本文提出利用GPT优化DistilBERT与T5生成的抽取式、生成式及混合式摘要,以最小化幻觉问题,并通过多指标评估验证了该方法能显著提升摘要的事实准确性与可靠性。

摘要:

在本研究中,我们使用DistilBERT模型生成抽取式摘要,并使用T5模型生成生成式摘要。此外,我们通过结合DistilBERT和T5模型生成混合式摘要。我们研究的核心是实施基于GPT的优化过程,以最小化AI生成摘要中常见的幻觉问题。我们评估未优化的摘要,并在优化后,使用一系列传统和新颖的指标评估优化后的摘要,证明摘要在准确性和可靠性方面有显著改进。结果突出显示了在减少幻觉内容方面的显著改进,从而提高了摘要的事实完整性。

英文摘要:

In this research, we uses the DistilBERT model to generate extractive summary and the T5 model to generate abstractive summaries. Also, we generate hybrid summaries by combining both DistilBERT and T5 models. Central to our research is the implementation of GPT-based refining process to minimize the common problem of hallucinations that happens in AI-generated summaries. We evaluate unrefined summaries and, after refining, we also assess refined summaries using a range of traditional and novel metrics, demonstrating marked improvements in the accuracy and reliability of the summaries. Results highlight significant improvements in reducing hallucinatory content, thereby increasing the factual integrity of the summaries.

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。

↑