Influence Tuning：通过实例属性和实例驱动更新降低虚假相关性
Influence Tuning: Demoting Spurious Correlations via Instance Attribution and Instance-Driven Updates
摘要：
深度学习NLP模型最关键的限制之一是缺乏可解释性，以及依赖于虚假的相关性。先前的工作提出了各种方法来解释黑盒模型，以揭示虚假的相关性，但该研究主要用于人机交互场景。它仍然是未充分探索是否或如何这样的模型解释可以用来自动“忘记”混淆功能。在这项工作中，我们提出了影响调整-一个利用模型解释来更新模型参数的过程，除了学习预测任务标签之外，还可以实现合理的解释（而不是依赖于数据中虚假模式的解释）。我们表明，在受控设置中，影响调整可以帮助从数据中的虚假模式中消除模型，显著优于使用对抗训练的基线方法。
英文摘要：
Among the most critical limitations of deep learning NLP models are their lack of interpretability, and their reliance on spurious correlations. Prior work proposed various approaches to interpreting the black-box models to unveil the spurious correlations, but the research was primarily used in human-computer interaction scenarios. It still remains underexplored whether or how such model interpretations can be used to automatically "unlearn" confounding features. In this work, we propose influence tuning--a procedure that leverages model interpretations to update the model parameters towards a plausible interpretation (rather than an interpretation that relies on spurious patterns in the data) in addition to learning to predict the task labels. We show that in a controlled setup, influence tuning can help deconfounding the model from spurious patterns in data, significantly outperforming baseline methods that use adversarial training.
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。
