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 2506.00985cs.CL
收藏

大语言模型是否理解我们为何写日记?一种目的提取与聚类方法

Do LLMs Understand Why We Write Diaries? A Method for Purpose Extraction and Clustering

European University at Saint Petersburg(圣彼得堡欧洲大学)

Valeriya Goloviznina, Alexander Sergeev, Mikhail Melnichenko, Evgeny Kotelnikov

AI总结:

本文提出基于大语言模型的日记写作目的提取与聚类方法,并在Prozhito苏联日记语料上验证,发现GPT-4o和o1-mini性能最佳,同时分析了目的分布与模型错误类型。

摘要:

日记分析面临诸多挑战,尤其是在从大规模语料库中提取有意义信息时,传统方法往往难以给出令人满意的结果。本研究提出一种基于大语言模型(LLMs)的新方法,用于识别并聚类日记写作的各种目的。所谓“目的”,指的是日记写作背后的意图,例如记录生活事件、进行自我反思或练习语言技能。我们将该方法应用于Prozhito数字档案中1922至1929年的苏联时期日记,该档案是一个丰富的个人叙事集合。我们对不同的专有和开源大语言模型进行了评估,发现GPT-4o和o1-mini取得了最佳性能,而基于模板的基线方法效果明显较差。此外,我们还依据作者性别、年龄和写作年份对提取出的目的进行了分析。进一步地,我们考察了模型所犯的错误类型,从而更深入地理解其局限性以及未来研究中潜在的改进方向。

英文摘要:

Diary analysis presents challenges, particularly in extracting meaningful information from large corpora, where traditional methods often fail to deliver satisfactory results. This study introduces a novel method based on Large Language Models (LLMs) to identify and cluster the various purposes of diary writing. By "purposes," we refer to the intentions behind diary writing, such as documenting life events, self-reflection, or practicing language skills. Our approach is applied to Soviet-era diaries (1922-1929) from the Prozhito digital archive, a rich collection of personal narratives. We evaluate different proprietary and open-source LLMs, finding that GPT-4o and o1-mini achieve the best performance, while a template-based baseline is significantly less effective. Additionally, we analyze the retrieved purposes based on gender, age of the authors, and the year of writing. Furthermore, we examine the types of errors made by the models, providing a deeper understanding of their limitations and potential areas for improvement in future research.

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。

↑