面向自然语言处理的新型忠实性中心可解释性范式
New Faithfulness-Centric Interpretability Paradigms for Natural Language Processing
AI总结：
本研究针对当前NLP模型可解释性方法的忠实性不足问题，提出构建可靠指标并开发忠实性可测模型（FMMs）和自解释两种新范式，解决了复杂通用神经NLP模型的忠实解释提供与确保难题。
摘要：
随着机器学习的普及及其在更关键应用中的使用，为这些模型提供解释以防止意外行为变得至关重要。遗憾的是，当前许多可解释性方法在忠实性方面存在不足。因此，本博士论文研究了“如何为复杂的通用神经自然语言处理（NLP）模型提供并确保忠实的解释？”这一问题。核心论点是我们应开发新的可解释性范式。这一目标通过首先构建可靠的忠实性指标，再将从该研究中获得的经验应用于开发新范式来实现。研究的两种新范式为忠实性可测模型（FMMs）和自解释。自解释的理念是让大型语言模型自我解释，我们发现当前模型无法持续做到这一点，但提出了实现方法。FMMs的理念是创建设计上使忠实性测量既经济又精确的模型，这使得优化解释以实现最大忠实性成为可能，因此FMMs是为可解释性而设计的。我们发现FMMs产生的解释在忠实性方面接近理论最优。总体而言，从所有关于忠实性的研究结果来看，事后解释和内在解释默认依赖于模型和任务。然而，使用FMMs时情况并非如此，即使采用相同的事后解释方法也是如此。这表明，即使对模型进行简单修改（如FMMs中对训练数据集的随机掩码），也能显著改变情况并产生持续忠实的解释。这回答了如何提供并确保忠实解释的问题。
英文摘要：
As machine learning becomes more widespread and is used in more critical applications, it's important to provide explanations for these models, to prevent unintended behavior. Unfortunately, many current interpretability methods struggle with faithfulness. Therefore, this Ph.D. thesis investigates the question "How to provide and ensure faithful explanations for complex general-purpose neural NLP models?" The main thesis is that we should develop new paradigms in interpretability. This is achieved by first developing solid faithfulness metrics and then applying the lessons learned from this investigation to develop new paradigms. The two new paradigms explored are faithfulness measurable models (FMMs) and self-explanations. The idea in self-explanations is to have large language models explain themselves, we identify that current models are not capable of doing this consistently. However, we suggest how this could be achieved. The idea of FMMs is to create models that are designed such that measuring faithfulness is cheap and precise. This makes it possible to optimize an explanation towards maximum faithfulness, which makes FMMs designed to be explained. We find that FMMs yield explanations that are near theoretical optimal in terms of faithfulness. Overall, from all investigations of faithfulness, results show that post-hoc and intrinsic explanations are by default model and task-dependent. However, this was not the case when using FMMs, even with the same post-hoc explanation methods. This shows, that even simple modifications to the model, such as randomly masking the training dataset, as was done in FMMs, can drastically change the situation and result in consistently faithful explanations. This answers the question of how to provide and ensure faithful explanations.
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。
