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 2409.14820cs.CLcs.AI
收藏

过去与当下的交汇:利用大语言模型构建历史类比

Past Meets Present: Creating Historical Analogy with Large Language Models

Fudan University(复旦大学);ByteDance Seed(字节跳动);MYbank, Ant Group(网商银行,蚂蚁集团)

Nianqi Li, Siyu Yuan, Jiangjie Chen, Jiaqing Liang, Feng Wei, Zujie Liang, Deqing Yang, Yanghua Xiao

AI总结:

针对历史类比获取难且AI领域相关研究不足的问题,本文探索了基于大语言模型的检索与生成式历史类比获取方法,提出自反思方法缓解幻觉与刻板印象,实验验证了方法的有效性。

摘要:

历史类比是将已知的过往事件与当代但不熟悉的事件进行比较的能力,是帮助人们决策和理解世界的重要能力。然而,应用史学领域的研究表明,人们很难找到恰当的类比,而AI领域的既往研究也忽视了历史类比这一方向。为填补这一空白,本文聚焦历史类比获取任务,其目标是为给定事件获取可类比的历史事件。我们探索了基于不同大语言模型(LLM)的检索式与生成式历史类比获取方法,还提出了一种自反思方法,以缓解LLM生成历史类比时出现的幻觉和刻板印象问题。通过人工评估与我们专门设计的多维度自动评估,我们发现LLM总体上具备良好的历史类比生成潜力,而使用我们提出的自反思方法可进一步提升模型性能。

英文摘要:

Historical analogies, which compare known past events with contemporary but unfamiliar events, are important abilities that help people make decisions and understand the world. However, research in applied history suggests that people have difficulty finding appropriate analogies. And previous studies in the AI community have also overlooked historical analogies. To fill this gap, in this paper, we focus on the historical analogy acquisition task, which aims to acquire analogous historical events for a given event. We explore retrieval and generation methods for acquiring historical analogies based on different large language models (LLMs). Furthermore, we propose a self-reflection method to mitigate hallucinations and stereotypes when LLMs generate historical analogies. Through human evaluations and our specially designed automatic multi-dimensional assessment, we find that LLMs generally have a good potential for historical analogies. And the performance of the models can be further improved by using our self-reflection method.

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。

↑