用于社交媒体立场检测的思维链嵌入
Chain-of-Thought Embeddings for Stance Detection on Social Media
AI总结：
本文提出COT Embeddings方法，将思维链推理嵌入传统RoBERTa立场检测流程，以解决社交媒体中隐含立场识别难题，并在多个数据集上取得SOTA性能。
摘要：
社交媒体上的立场检测对大型语言模型（LLMs）而言具有挑战性，因为在线对话中不断涌现的俚语和口语化表达往往包含深度隐含的立场标签。思维链（COT）提示最近已被证明能够提升立场检测任务的性能——缓解了其中一些问题。然而，COT提示在隐含立场识别方面仍然存在困难。这一挑战的出现是因为许多样本在模型熟悉与不同主题相关的俚语和不断演变的知识之前，最初难以理解，而所有这些都需要通过训练数据来获取。在本研究中，我们通过引入COT Embeddings来解决这一问题，该方法通过嵌入COT推理并将其整合到传统的基于RoBERTa的立场检测流程中，从而提升COT在立场检测任务上的性能。我们的分析表明：1）文本编码器能够利用带有轻微错误或幻觉的COT推理，而这些错误或幻觉原本会扭曲COT输出标签。2）当一个样本的预测高度依赖领域特定模式时，文本编码器可以忽略具有误导性的COT推理。我们的模型在多个从社交媒体收集的立场检测数据集上取得了SOTA性能。
英文摘要：
Stance detection on social media is challenging for Large Language Models (LLMs), as emerging slang and colloquial language in online conversations often contain deeply implicit stance labels. Chain-of-Thought (COT) prompting has recently been shown to improve performance on stance detection tasks -- alleviating some of these issues. However, COT prompting still struggles with implicit stance identification. This challenge arises because many samples are initially challenging to comprehend before a model becomes familiar with the slang and evolving knowledge related to different topics, all of which need to be acquired through the training data. In this study, we address this problem by introducing COT Embeddings which improve COT performance on stance detection tasks by embedding COT reasonings and integrating them into a traditional RoBERTa-based stance detection pipeline. Our analysis demonstrates that 1) text encoders can leverage COT reasonings with minor errors or hallucinations that would otherwise distort the COT output label. 2) Text encoders can overlook misleading COT reasoning when a sample's prediction heavily depends on domain-specific patterns. Our model achieves SOTA performance on multiple stance detection datasets collected from social media.
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。
