The Mutual Reinforcement Effect (MRE) investigates the synergistic relationship between word-level and text-level classifications in text classification tasks. It posits that the performance of both classification levels can be mutually enhanced. However, this mechanism has not been adequately demonstrated or explained in prior research. To address this gap, we employ information flow analysis to observe and substantiate the MRE theory. Our experiments on six MRE hybrid datasets revealed the presence of MRE in the model and its impact. Additionally, we conducted fine-tuning experiments, whose results were consistent with those of the information flow experiments. The convergence of findings from both experiments corroborates the existence of MRE. Furthermore, we extended the application of MRE to prompt learning, utilizing word-level information as a verbalizer to bolster the model's prediction of text-level classification labels. In our final experiment, the F1-score significantly surpassed the baseline in five out of six datasets, further validating the notion that word-level information enhances the language model's comprehension of the text as a whole.

翻译：互增强效应（Mutual Reinforcement Effect, MRE）探究文本分类任务中词级分类与文本级分类之间的协同关系，认为两个分类层次的性能可以相互提升。然而，该机制在既往研究中尚未得到充分论证或解释。为填补这一空白，我们采用信息流分析方法观察并验证MRE理论。在六个MRE混合数据集上的实验揭示了模型中MRE的存在及其影响。此外，我们开展了微调实验，其结果与信息流实验结果一致。两类实验结果的趋同共同印证了MRE的存在。进一步地，我们将MRE扩展至提示学习领域，利用词级信息作为语言表达器，强化模型对文本级分类标签的预测能力。在最终实验中，六个数据集中有五个数据集的F1分数显著超越基线，这进一步验证了词级信息能够增强语言模型对整体文本的理解能力。