气候错误信息的生成式辟谣
Generative Debunking of Climate Misinformation
AI总结：
针对气候错误信息难以大规模纠正的问题，本文提出融合逆向主张分类与谬误检测的 LLM 提示框架，使 GPT-4、Mixtral 等模型生成“真相三明治”式辟谣，并发布数据集、代码和演示。
摘要：
有关气候变化的错误信息会造成诸多负面影响，因此有必要采取纠正性回应。心理学研究提出了多种降低气候错误信息影响的策略，例如事实—迷思—谬误—事实结构。然而，在实际中大规模实施纠正性干预仍是一项挑战。自动检测并纠正错误信息为该问题提供了一种解决方案。本研究记录了大型语言模型的开发过程：这些模型接收一条气候迷思作为输入，并通过将逆向主张分类和谬误检测纳入 LLM 提示框架，生成遵循事实—迷思—谬误—事实（“真相三明治”）结构的辟谣内容。我们将开放模型（Mixtral、Palm2）和专有模型（GPT-4）与复杂程度不同的提示策略相结合。实验表明，GPT-4 和 Mixtral 在结合结构化提示时表现出良好性能。我们识别了辟谣生成和人工评估中的具体挑战，并规划了未来工作方向。我们公开发布了一个高质量真相三明治辟谣数据集、源代码以及该辟谣系统的演示。
英文摘要：
Misinformation about climate change causes numerous negative impacts, necessitating corrective responses. Psychological research has offered various strategies for reducing the influence of climate misinformation, such as the fact-myth-fallacy-fact-structure. However, practically implementing corrective interventions at scale represents a challenge. Automatic detection and correction of misinformation offers a solution to the misinformation problem. This study documents the development of large language models that accept as input a climate myth and produce a debunking that adheres to the fact-myth-fallacy-fact (``truth sandwich'') structure, by incorporating contrarian claim classification and fallacy detection into an LLM prompting framework. We combine open (Mixtral, Palm2) and proprietary (GPT-4) LLMs with prompting strategies of varying complexity. Experiments reveal promising performance of GPT-4 and Mixtral if combined with structured prompts. We identify specific challenges of debunking generation and human evaluation, and map out avenues for future work. We release a dataset of high-quality truth-sandwich debunkings, source code and a demo of the debunking system.
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。
