发表机构
Universidade Estadual de Campinas (UNICAMP)（坎皮纳斯州立大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究探讨向文本添加句法和修辞信息能否提升连贯性评估，发现现有架构下纯文本效果更佳，并验证了连贯性可作为检测误导性内容的代理指标。
AI 中文摘要
大型语言模型的最新进展已改变了人机交互方式。尽管这些模型生成流畅，但往往产生语法正确而语义不连贯的文本，包含矛盾或逻辑流程中断。本研究探讨了向文本添加句法和修辞信息是否能改善不连贯性预测。我们的实验和分析表明，纯文本取得了更高的准确率，因为添加的信息在结构和句法上与语言模型的架构不兼容。此外，为了展示连贯性评估的实际重要性，我们在一个巴西虚假信息数据集上进行了零样本实验，结果表明文本连贯性可以作为检测误导性内容的代理指标。代码和模型可在该https URL获取。
英文摘要
Recent advances in large language models have transformed human-computer interaction. Despite their fluency, these models often produce texts that are grammatically correct but semantically incoherent, containing contradictions or disruptions in logical flow. This work investigates whether enriching text with syntactic and rhetorical information can improve incoherence prediction. Our experiments and analysis show that plain texts achieved higher accuracy because the added information was structurally and syntactically incompatible with the language model's architecture. Additionally, to demonstrate the practical importance of coherence assessment, we performed zero-shot experiments on a Brazilian disinformation dataset, suggesting that textual coherence can serve as a proxy for detecting misleading content. Code and models are available at https://github.com/ittozzamV/cohereclassifier.
Comments6 figures, 8 tables, 10 pages
