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 2401.03346cs.CYcs.AIcs.CLcs.LGcs.SI
收藏

大型语言模型在真实世界仇恨言论检测中的应用研究

An Investigation of Large Language Models for Real-World Hate Speech Detection

University at Buffalo（纽约州立大学布法罗分校）；University of Texas at San Antonio（德克萨斯大学圣安东尼奥分校）；Union County Magnet High School（联合县磁石高中）；East Chapel Hill High School（东教堂山高中）；Minhang Corsspoint Academy（闵行交汇点学院）

Keyan Guo, Alexander Hu, Jaden Mu, Ziheng Shi, Ziming Zhao, Nishant Vishwamitra, Hongxin Hu

备注：
Accepted for publication on 22nd International Conference of Machine Learning and Applications, ICMLA 2023
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

本研究针对在线仇恨言论检测的上下文依赖问题，利用五个数据集评估大型语言模型（LLMs），并提出四种提示策略，发现精心设计的推理提示能充分利用LLMs知识库捕捉上下文，显著超越现有基准模型。

摘要：

仇恨言论已成为当今困扰我们社会空间的一个主要问题。尽管已有重大努力来解决这一问题，但现有方法在有效检测在线仇恨言论方面仍存在显著局限。现有方法的一个主要局限在于，仇恨言论检测是一个高度依赖上下文的问题，而这些方法无法完全捕捉仇恨言论的上下文以做出准确预测。近期，大型语言模型（LLMs）在多项自然语言任务中展现了最先进的性能。LLMs 使用海量自然语言数据进行了广泛训练，使其能够掌握复杂的上下文细节。因此，它们可以作为上下文感知仇恨言论检测的知识库。然而，使用 LLMs 检测仇恨言论的一个根本问题是，目前缺乏关于如何有效地为 LLMs 设计提示以进行上下文感知仇恨言论检测的研究。在本研究中，我们采用五个公认的仇恨言论数据集，对仇恨言论检测进行了大规模研究。我们发现，LLMs 不仅匹敌，而且往往在识别仇恨言论方面超越了当前基准机器学习模型的性能。通过提出四种多样化的提示策略，以优化 LLMs 在检测仇恨言论中的使用。我们的研究表明，精心设计的推理提示能够通过充分利用 LLMs 中的知识库，有效捕捉仇恨言论的上下文，显著优于现有技术。此外，尽管 LLMs 能够为仇恨言论的上下文检测提供丰富的知识库，但合适的提示策略在有效利用该知识库进行高效检测方面发挥着至关重要的作用。

英文摘要：

Hate speech has emerged as a major problem plaguing our social spaces today. While there have been significant efforts to address this problem, existing methods are still significantly limited in effectively detecting hate speech online. A major limitation of existing methods is that hate speech detection is a highly contextual problem, and these methods cannot fully capture the context of hate speech to make accurate predictions. Recently, large language models (LLMs) have demonstrated state-of-the-art performance in several natural language tasks. LLMs have undergone extensive training using vast amounts of natural language data, enabling them to grasp intricate contextual details. Hence, they could be used as knowledge bases for context-aware hate speech detection. However, a fundamental problem with using LLMs to detect hate speech is that there are no studies on effectively prompting LLMs for context-aware hate speech detection. In this study, we conduct a large-scale study of hate speech detection, employing five established hate speech datasets. We discover that LLMs not only match but often surpass the performance of current benchmark machine learning models in identifying hate speech. By proposing four diverse prompting strategies that optimize the use of LLMs in detecting hate speech. Our study reveals that a meticulously crafted reasoning prompt can effectively capture the context of hate speech by fully utilizing the knowledge base in LLMs, significantly outperforming existing techniques. Furthermore, although LLMs can provide a rich knowledge base for the contextual detection of hate speech, suitable prompting strategies play a crucial role in effectively leveraging this knowledge base for efficient detection.

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。

↑