arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2501.13802cs.CY
收藏

通过人类监督增强大语言模型在治理中的应用:评估和对齐大语言模型在气候错误信息专家分类上的表现,以检测关于气候变化的虚假或误导性声明

Enhancing LLMs for Governance with Human Oversight: Evaluating and Aligning LLMs on Expert Classification of Climate Misinformation for Detecting False or Misleading Claims about Climate Change

Mowafak Allaham, Ayse D. Lokmanoglu, P. Sol Hart, Erik C. Nisbet

AI总结:

本文评估了大语言模型在气候错误信息分类中的表现,发现专有模型优于开源模型,且基于专家标注数据微调GPT-3.5-turbo可达到资深专家水平,证明人类监督与专家数据对齐能提升LLMs在专业治理任务中的能力。

摘要:

气候错误信息是一个可能因大语言模型(LLMs)的发展而被显著加剧的问题。在本研究中,我们评估了LLMs成为缓解在线虚假/错误信息解决方案的一部分而非问题本身的潜力。我们使用一个公开的专家标注数据集和一个经过筛选的社交媒体内容样本,评估了专有模型与开源LLMs在气候错误信息分类任务上的表现,并将其与现有的以气候为重点的计算机辅助工具和专家评估进行比较。结果表明:(1)开源模型在分类气候错误信息方面显著落后于专有模型;(2)现有的利用专家标注数据集的以气候为重点的计算机辅助工具继续优于许多专有模型,包括GPT-4o;(3)证明了在专家标注数据集上微调GPT-3.5-turbo在分类气候变化相关声明方面的有效性和泛化能力,其水平与拥有超过20年气候传播经验的气候变化专家相当。这些发现强调了以下两点:1)在训练LLMs时纳入人类监督(例如纳入专家标注数据集)对于需要主题专业知识(如分类气候错误信息)的治理任务的重要性;2)LLMs在促进公民社会组织参与各种治理任务方面的潜力,例如在气候变化以外的领域(如政治和健康科学)分类虚假或误导性声明。

英文摘要:

Climate misinformation is a problem that has the potential to be substantially aggravated by the development of Large Language Models (LLMs). In this study we evaluate the potential for LLMs to be part of the solution for mitigating online dis/misinformation rather than the problem. Employing a public expert annotated dataset and a curated sample of social media content we evaluate the performance of proprietary vs. open source LLMs on climate misinformation classification task, comparing them to existing climate-focused computer-assisted tools and expert assessments. Results show (1) open-source models substantially under-perform in classifying climate misinformation compared to proprietary models, (2) existing climate-focused computer-assisted tools leveraging expert-annotated datasets continues to outperform many of proprietary models, including GPT-4o, and (3) demonstrate the efficacy and generalizability of fine-tuning GPT-3.5-turbo on expert annotated dataset in classifying claims about climate change at the equivalency of climate change experts with over 20 years of experience in climate communication. These findings highlight 1) the importance of incorporating human-oversight, such as incorporating expert-annotated datasets in training LLMs, for governance tasks that require subject-matter expertise like classifying climate misinformation, and 2) the potential for LLMs in facilitating civil society organizations to engage in various governance tasks such as classifying false or misleading claims in domains beyond climate change such as politics and health science.

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。

↑