Make Up Your Mind! Adversarial Generation of Inconsistent Natural Language Explanations

Abstract

To increase trust in artificial intelligence systems, a promising research direction consists of designing neural models capable of generating natural language explanations for their predictions. In this work, we show that such models are nonetheless prone to generating mutually inconsistent explanations, such as "Because there is a dog in the image." and "Because there is no dog in the [same] image.", exposing flaws in either the decision-making process of the model or in the generation of the explanations. We introduce a simple yet effective adversarial framework for sanity checking models against the generation of inconsistent natural language explanations. Moreover, as part of the framework, we address the problem of adversarial attacks with full target sequences, a scenario that was not previously addressed in sequence-to-sequence attacks. Finally, we apply our framework on a state-of-the-art neural natural language inference model that provides natural language explanations for its predictions. Our framework shows that this model is capable of generating a significant number of inconsistent explanations.

A Review on Explainability in Multimodal Deep Neural Nets

“…Hence, they can offer diagnostic strengths that help understand the model working mechanism, model debugging i.e.to identify flaws in the model and ensure whether the model works as intended. The multimodal explainability models can also identify adversarial attacks and defense mechanisms [169], fairness and bias [13], providing scope for troubleshooting, rectification, improving overall model performance, predictive and explanatory power.…”

Knowledge-Guided Sentiment Analysis Via Learning From Natural Language Explanations

“…In this section, we will briefly review related works on the sentiment classification [11,13], knowledge-aware sentiment analysis [9,14], and natural language explanation [5,16,23] classification. Sentiment Analysis Sentiment analysis and emotion recognition have always attracted attention in multiple fields such as NL processing, psychology, and cognitive science.…”

Prompting Contrastive Explanations for Commonsense Reasoning Tasks

“…However, the space of possible free-form explanations is incredibly large, inherently ambiguous, and difficult to annotate or evaluate (Wiegreffe et al, 2020;Latcinnik and Berant, 2020). Furthermore, quantifying the model's dependence on free-form explanations is also challenging (Camburu et al, 2020). We address these challenges by proposing an unsupervised method that uses contrastive prompts, which require the model to explicitly contrast different possible answers in its explanation (Table 1).…”