Human Interpretation of Saliency-based Explanation Over Text
Bosch Center for Artificial Intelligence（博世人工智能中心）；University of Stuttgart（斯图加特大学）；Bar Ilan University（巴伊兰大学）；Allen Institute for Artificial Intelligence（艾伦人工智能研究所）
Hendrik Schuff, Alon Jacovi, Heike Adel, Yoav Goldberg, Ngoc Thang Vu
While a lot of research in explainable AI focuses on producing effective explanations, less work is devoted to the question of how people understand and interpret the explanation. In this work, we focus on this question through a study of saliency-based explanations over textual data. Feature-attribution explanations of text models aim to communicate which parts of the input text were more influential than others towards the model decision. Many current explanation methods, such as gradient-based or Shapley value-based methods, provide measures of importance which are well-understood mathematically. But how does a person receiving the explanation (the explainee) comprehend it? And does their understanding match what the explanation attempted to communicate? We empirically investigate the effect of various factors of the input, the feature-attribution explanation, and visualization procedure, on laypeople's interpretation of the explanation. We query crowdworkers for their interpretation on tasks in English and German, and fit a GAMM model to their responses considering the factors of interest. We find that people often mis-interpret the explanations: superficial and unrelated factors, such as word length, influence the explainees' importance assignment despite the explanation communicating importance directly. We then show that some of this distortion can be attenuated: we propose a method to adjust saliencies based on model estimates of over- and under-perception, and explore bar charts as an alternative to heatmap saliency visualization. We find that both approaches can attenuate the distorting effect of specific factors, leading to better-calibrated understanding of the explanation.
As the applications of Natural Language Processing (NLP) in sensitive areas like Political Profiling, Review of Essays in Education, etc. proliferate, there is a great need for increasing transparency in NLP models to build trust with stakeholders and identify biases. A lot of work in Explainable AI has aimed to devise explanation methods that give humans insights into the workings and predictions of NLP models. While these methods distill predictions from complex models like Neural Networks into consumable explanations, how humans understand these explanations is still widely unexplored. Inna…
Beyond saliency: enhancing explanation of speech emotion recognition with expert-referenced acoustic cues
Center for Cognitive Interaction Technology (CITEC), Bielefeld University, Germany（认知交互技术中心（CITEC），比勒菲尔德大学，德国）；Cognitive Systems Lab, University of Bremen, Germany（认知系统实验室，不莱梅大学，德国）
Saliency strikes back: How filtering out high frequencies improves white-box explanations
Carney Institute for Brain Science, Brown University（布朗大学卡尼脑科学研究所）；CerCo, CNRS（法国国家科学研究中心CerCo研究所）；SNCF（法国国家铁路公司）；Institute of Mathematics of Toulouse, University Paul Sabatier（保罗萨巴蒂埃大学图卢兹数学研究所）
Rutgers University–Newark（罗格斯大学纽瓦克分校）；Institute for Advanced Study（普林斯顿高等研究院）
The goal of explainable Artificial Intelligence (XAI) is to generate human-interpretable explanations, but there are no computationally precise theories of how humans interpret AI generated explanations. The lack of theory means that validation of XAI must be done empirically, on a case-by-case basis, which prevents systematic theory-building in XAI. We propose a psychological theory of how humans draw conclusions from saliency maps, the most common form of XAI explanation, which for the first time allows for precise prediction of explainee inference conditioned on explanation. Our theory posi…
Huawei Technologies（华为技术有限公司）；Hong Kong University of Science and Technology（香港科技大学）
It has been long debated that eXplainable AI (XAI) is an important topic, but it lacks rigorous definition and fair metrics. In this paper, we briefly summarize the status quo of the metrics, along with an exhaustive experimental study based on them, including faithfulness, localization, false-positives, sensitivity check, and stability. With the experimental results, we conclude that among all the methods we compare, no single explanation method dominates others in all metrics. Nonetheless, Gradient-weighted Class Activation Mapping (Grad-CAM) and Randomly Input Sampling for Explanation (RISE…
Machine learning models need to provide contrastive explanations, since people often seek to understand why a puzzling prediction occurred instead of some expected outcome. Current contrastive explanations are rudimentary comparisons between examples or raw features, which remain difficult to interpret, since they lack semantic meaning. We argue that explanations must be more relatable to other concepts, hypotheticals, and associations. Inspired by the perceptual process from cognitive psychology, we propose the XAI Perceptual Processing Framework and RexNet model for relatable explainable AI …
TU Berlin（柏林工业大学）；Fraunhofer HHI（弗劳恩霍夫海因里希·赫兹研究所）；Leibniz Institute of Agricultural Engineering and Bioeconomy e.V. (ATB)（莱布尼茨农业工程与生物经济研究所）；BIFOLD – Berlin Institute for the Foundations of Learning and Data（柏林学习与数据基础研究所）；University of Potsdam（波茨坦大学）
Classification Metrics for Image Explanations: Towards Building Reliable XAI-Evaluations
Fraunhofer Institute for Manufacturing Engineering and Automation IPA（弗劳恩霍夫制造工程与自动化研究所）；Institute of Industrial Manufacturing and Management IFF, University of Stuttgart（斯图加特大学工业制造与管理研究所）
On the explainable properties of 1-Lipschitz Neural Networks: An Optimal Transport Perspective
Université Paul-Sabatier（保罗萨巴蒂尔大学）；Institut de Recherche Technologique Saint-Exupéry（圣埃克苏佩里技术研究院）；Carney Institute for Brain Science,Brown University（布朗大学卡尼脑科学研究所）；Innovation & Research Division, SNCF（法国国家铁路公司创新与研究部）
EXplainable AI (XAI) methods have been proposed to interpret how a deep neural network predicts inputs through model saliency explanations that highlight the parts of the inputs deemed important to arrive a decision at a specific target. However, it remains challenging to quantify correctness of their interpretability as current evaluation approaches either require subjective input from humans or incur high computation cost with automated evaluation. In this paper, we propose backdoor trigger patterns--hidden malicious functionalities that cause misclassification--to automate the evaluation of…
Explainable AI is an emerging field providing solutions for acquiring insights into automated systems' rationale. It has been put on the AI map by suggesting ways to tackle key ethical and societal issues. Existing explanation techniques are often not comprehensible to the end user. Lack of evaluation and selection criteria also makes it difficult for the end user to choose the most suitable technique. In this study, we combine logic-based argumentation with Interpretable Machine Learning, introducing a preliminary meta-explanation methodology that identifies the truthful parts of feature impo…
University of Southern California（南加州大学）；IIT Delhi（印度理工学院德里分校）
Augmenting pre-trained language models with knowledge graphs (KGs) has achieved success on various commonsense reasoning tasks. However, for a given task instance, the KG, or certain parts of the KG, may not be useful. Although KG-augmented models often use attention to focus on specific KG components, the KG is still always used, and the attention mechanism is never explicitly taught which KG components should be used. Meanwhile, saliency methods can measure how much a KG feature (e.g., graph, node, path) influences the model to make the correct prediction, thus explaining which KG features a…
Neighboring Words Affect Human Interpretation of Saliency Explanations
Bar Ilan University（巴伊兰大学）；Bosch Center for Artificial Intelligence（博世人工智能中心）；University of Stuttgart（斯图加特大学）；Allen Institute for Artificial Intelligence（艾伦人工智能研究所）
There is a recent surge of interest in using attention as explanation of model predictions, with mixed evidence on whether attention can be used as such. While attention conveniently gives us one weight per input token and is easily extracted, it is often unclear toward what goal it is used as explanation. We find that often that goal, whether explicitly stated or not, is to find out what input tokens are the most relevant to a prediction, and that the implied user for the explanation is a model developer. For this goal and user, we argue that input saliency methods are better suited, and that…
Deep learning has emerged as a compelling solution to many NLP tasks with remarkable performances. However, due to their opacity, such models are hard to interpret and trust. Recent work on explaining deep models has introduced approaches to provide insights toward the model's behaviour and predictions, which are helpful for assessing the reliability of the model's predictions. However, such methods do not improve the model's reliability. In this paper, we aim to teach the model to make the right prediction for the right reason by providing explanation training and ensuring the alignment of th…
Saliency map generation techniques are at the forefront of explainable AI literature for a broad range of machine learning applications. Our goal is to question the limits of these approaches on more complex tasks. In this paper we apply Layer-Wise Relevance Propagation (LRP) to a sequence-to-sequence attention model trained on a text summarization dataset. We obtain unexpected saliency maps and discuss the rightfulness of these "explanations". We argue that we need a quantitative way of testing the counterfactual case to judge the truthfulness of the saliency maps. We suggest a protocol to ch…
Center for Language and Speech Processing（语言与语音处理中心）；Johns Hopkins University（约翰霍普金斯大学）
Saliency methods are widely used to interpret neural network predictions, but different variants of saliency methods often disagree even on the interpretations of the same prediction made by the same model. In these cases, how do we identify when are these interpretations trustworthy enough to be used in analyses? To address this question, we conduct a comprehensive and quantitative evaluation of saliency methods on a fundamental category of NLP models: neural language models. We evaluate the quality of prediction interpretations from two perspectives that each represents a desirable property …
Center for Language and Speech Processing（语言与语音处理中心）；Johns Hopkins University（约翰斯·霍普金斯大学）
Despite their original goal to jointly learn to align and translate, Neural Machine Translation (NMT) models, especially Transformer, are often perceived as not learning interpretable word alignments. In this paper, we show that NMT models do learn interpretable word alignments, which could only be revealed with proper interpretation methods. We propose a series of such methods that are model-agnostic, are able to be applied either offline or online, and do not require parameter update or architectural change. We show that under the force decoding setup, the alignments induced by our interpret…
Fool Me Once? Contrasting Textual and Visual Explanations in a Clinical Decision-Support Setting
Vienna University of Technology（维也纳工业大学）；University of Oxford（牛津大学）；Rayscape（锐景）；Oxford University Hospitals NHS Foundation Trust（牛津大学医院NHS基金会信托）；University College London（伦敦大学学院）
Microsoft（微软）；Tel-Aviv University（特拉维夫大学）；The Open University（开放大学）；Bar-Ilan University（巴伊兰大学）
Recently, there has been growing interest in the ability of Transformer-based models to produce meaningful embeddings of text with several applications, such as text similarity. Despite significant progress in the field, the explanations for similarity predictions remain challenging, especially in unsupervised settings. In this work, we present an unsupervised technique for explaining paragraph similarities inferred by pre-trained BERT models. By looking at a pair of paragraphs, our technique identifies important words that dictate each paragraph's semantics, matches between the words in both …
