ChatGPT 与媒体偏见：GPT-3.5 与微调语言模型的比较研究
ChatGPT v.s. Media Bias: A Comparative Study of GPT-3.5 and Fine-tuned Language Models
AI总结：
本研究利用 MBIB 基准比较 ChatGPT 与微调模型在六类媒体偏见检测上的表现，发现 ChatGPT 在仇恨言论和文本级语境偏见上表现相当，但在假新闻、种族、性别和认知偏见等细微检测上存在困难。
摘要：
在快速演变的数字领域中，识别媒体偏见的能力变得至关重要，因为它能够塑造公众情绪并影响关键决策。大型语言模型（LLMs）如 ChatGPT 的出现，因其在各类自然语言处理（NLP）任务中的广泛实用性，引发了对其在媒体偏见检测中有效性的探索。ChatGPT 能否检测媒体偏见？本研究旨在通过利用媒体偏见识别基准（MBIB）来回答这一问题，评估 ChatGPT 在区分六类媒体偏见方面的能力，并与 BART、ConvBERT 和 GPT-2 等微调模型进行对比。研究结果呈现出一种二元分化：ChatGPT 在检测仇恨言论和文本级语境偏见方面与微调模型表现相当，但在其他偏见检测的较细微要素上遇到困难，即假新闻、种族、性别和认知偏见。
英文摘要：
In our rapidly evolving digital sphere, the ability to discern media bias becomes crucial as it can shape public sentiment and influence pivotal decisions. The advent of large language models (LLMs), such as ChatGPT, noted for their broad utility in various natural language processing (NLP) tasks, invites exploration of their efficacy in media bias detection. Can ChatGPT detect media bias? This study seeks to answer this question by leveraging the Media Bias Identification Benchmark (MBIB) to assess ChatGPT's competency in distinguishing six categories of media bias, juxtaposed against fine-tuned models such as BART, ConvBERT, and GPT-2. The findings present a dichotomy: ChatGPT performs at par with fine-tuned models in detecting hate speech and text-level context bias, yet faces difficulties with subtler elements of other bias detections, namely, fake news, racial, gender, and cognitive biases.
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。
