arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.00345cs.CL
收藏

IndiVec:利用大语言模型结合细粒度偏见指标进行媒体偏见检测的探索

IndiVec: An Exploration of Leveraging Large Language Models for Media Bias Detection with Fine-Grained Bias Indicators

The Chinese University of Hong Kong(香港中文大学);MoE Key Laboratory of High Confidence Software Technologies(教育部高可信软件技术重点实验室);The Hong Kong Polytechnic University(香港理工大学)

Luyang Lin, Lingzhi Wang, Xiaoyan Zhao, Jing Li, Kam-Fai Wong

AI总结:

本研究提出基于大语言模型的通用媒体偏见检测框架IndiVec,通过构建细粒度偏见数据库并自动选取指标进行多数投票,在四个政治偏见数据集上显著优于基线,兼具适应性与可解释性。

摘要:

本研究聚焦于媒体偏见检测,这在社交媒体平台影响个人态度和观点的当今时代至关重要。与以往主要依赖针对特定数据集训练特定模型、导致适应性有限且在域外数据上表现不佳的工作不同,我们引入了一个基于大语言模型的通用偏见检测框架IndiVec。IndiVec首先利用大语言模型强大的指令跟随能力和向量数据库技术,构建一个细粒度的媒体偏见数据库。当面对新的输入进行偏见检测时,我们的框架自动从向量数据库中选取最相关的指标,并采用多数投票来确定输入的偏见标签。IndiVec相较于以往方法表现出色,这得益于其适应性(在来自不同来源的多个数据集上展现出一致的性能)和可解释性(提供明确的top-k指标来解释偏见预测)。在四个政治偏见数据集上的实验结果表明,IndiVec显著优于基线方法。此外,额外的实验和分析为框架的有效性提供了深刻的见解。

英文摘要:

This study focuses on media bias detection, crucial in today's era of influential social media platforms shaping individual attitudes and opinions. In contrast to prior work that primarily relies on training specific models tailored to particular datasets, resulting in limited adaptability and subpar performance on out-of-domain data, we introduce a general bias detection framework, IndiVec, built upon large language models. IndiVec begins by constructing a fine-grained media bias database, leveraging the robust instruction-following capabilities of large language models and vector database techniques. When confronted with new input for bias detection, our framework automatically selects the most relevant indicator from the vector database and employs majority voting to determine the input's bias label. IndiVec excels compared to previous methods due to its adaptability (demonstrating consistent performance across diverse datasets from various sources) and explainability (providing explicit top-k indicators to interpret bias predictions). Experimental results on four political bias datasets highlight IndiVec's significant superiority over baselines. Furthermore, additional experiments and analysis provide profound insights into the framework's effectiveness.

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。

↑