Generating Counterfactual Explanations with Natural Language

By Lisa Anne Hendricks, Ronghang Hu, Trevor Darrell, Zeynep Akata. 2018

102 citations recorded by the source corpus.

Natural language explanations of deep neural network decisions provide an intuitive way for a AI agent to articulate a reasoning process. Current textual explanations learn to discuss class discriminative features in an image. However, it is also helpful to understand which attributes might change a classification decision if present in an image (e.g., "This is not a Scarlet Tanager because it does not have black wings.") We call such textual explanations counterfactual explanations, and propose an intuitive method to generate counterfactual explanations by inspecting which evidence in an input is missing, but might contribute to a different classification decision if present in the image. To demonstrate our method we consider a fine-grained image classification task in which we take as input an image and a counterfactual class and output text which explains why the image does not belong to a counterfactual class. We then analyze our generated counterfactual explanations both qualitatively and quantitatively using proposed automatic metrics.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Causal Interpretability for Machine Learning - Problems, Methods and Evaluation (2020, methodology): “Traditional Interpretability Interpretable Models: [106], [103], [64], [102], [65], [105], [50], [13], [40] Causal Interpretability Model-based: [77], [38], [12], [8], [112], [81], [7], Example-based: [35], [45], [39], [101], [76], [86], [73], [61], [60], [33], [34] Post-hoc: [47], [89], [66], [93],”
Explaining Classifiers with Causal Concept Effect (CaCE) (2019, neutral): “Many interpretability methods developed to have causal-ﬂavor are for local explanations, such as removing and adding pixels to generate counterfactual explanations for images [5, 1] or for texts [7].”
NILE : Natural Language Inference with Faithful Natural Language Explanations (2020, background): “Hendricks et al. (2018) produce counterfactual natural language explanations for image classi-ﬁcation given an image and a counter-class label.”
Explainable artificial intelligence (XAI), the goodness criteria and the grasp-ability test (2018, unknown): “Now move on to an hypothetical XAI case that I create based on an existing XAI work [9] (see Figure 2).”
The Use and Misuse of Counterfactuals in Ethical Machine Learning (2021, background): “The use of counterfactuals has become increasingly popular in the machine learning community for many reasons such as making sense of algorithmic fairness or explainability in automated decision-making for consequential social contexts [4, 9, 14, 18, 29, 35, 42, 47, 51].”
Teach Me to Explain: A Review of Datasets for Explainable Natural Language Processing (2021, background): “[49] Lisa Anne Hendricks, Ronghang Hu, Trevor Darrell, and Zeynep Akata.”
Counterfactual Explanations and Algorithmic Recourses for Machine Learning: A Review (2020, unknown): “…the readers to the papers that propose algorithms targeted towards other data modalities: (1) Image Data : [1, 8, 9, 12, 13, 29, 77, 104, 109, 114, 128, 135, 142, 146, 151, 161, 163, 168, 169, 191, 192, 207, 217, 218, 237, 255, 256, 266, 284, 291, 304, 320, 333, 334, 340, 347, 359, 368, 370, 377].”
The hidden assumptions behind counterfactual explanations and principal reasons (2019, background): “Recent proposals from computer scientists have focused on generating counterfactual explanations for the decisions of a machine learning model [27, 47, 44, 29, 20, 17, 15, 34, 25, 9].”
Generating Counterfactual and Contrastive Explanations using SHAP (2019, methodology): “One such example is of Hendricks et all [ Hendricks et al. , 2018] wherein they use an explanation model to predict candidate counterfactual evidence on images, or evidence which is discriminative for a counter-class.”