Abstract
Despite the overwhelming performance improvements offered by recent natural language procesing (NLP) models, the decisions made by these models are largely a black box. Towards closing this gap, the field of causal NLP combines causal inference literature with modern NLP models to elucidate causal effects of text features. We replicate and extend Bansal et al's work on regularizing text classifiers to adhere to estimated effects, focusing instead on model interpretability. Specifically, we focus on developing a two-headed RieszNet-based neural network architecture which achieves better treatment effect estimation accuracy. Our framework, CausalSent, accurately predicts treatment effects in semi-synthetic IMDB movie reviews, reducing MAE of effect estimates by 2-3x compared to Bansal et al's MAE on synthetic Civil Comments data. With an ensemble of validated models, we perform an observational case study on the causal effect of the word "love" in IMDB movie reviews, finding that the presence of the word "love" causes a +2.9% increase in the probability of a positive sentiment.
Abstract (translated)
尽管最近的自然语言处理（NLP）模型提供了显著的性能改进，但这些模型做出决策的过程仍然很大程度上是一个黑盒。为了填补这一空白，因果NLP领域将因果推理文献与现代NLP模型结合在一起，以阐明文本特征的因果效应。我们复制并扩展了Bansal等人关于通过正则化使文本分类器遵循估计效果的工作，并侧重于提高模型可解释性。具体而言，我们专注于开发一种基于RieszNet的双头神经网络架构，该架构在治疗效果估计准确性方面表现更好。 我们的框架CausalSent能够在半合成IMDB电影评论数据上准确预测治疗效应，与Bansal等人在合成Civil Comments数据上的平均绝对误差（MAE）相比，我们对效果估计的MAE减少了2到3倍。通过使用一组经过验证的模型进行集合分析，我们在IMDB电影评论中进行了观察性案例研究，以探究单词“love”的因果效应，发现该词的存在使正面情感的概率增加了+2.9%。
URL
https://arxiv.org/abs/2508.17576
