Let the CAT out of the bag: Contrastive Attributed explanations for Text
Contrastive explanations for understanding the behavior of black box models has gained a lot of attention recently as they provide potential for recourse. In this paper, we propose a method Contrastive Attributed explanations for Text (CAT) which provides contrastive explanations for natural language text data with a novel twist as we build and exploit attribute classifiers leading to more semantically meaningful explanations. To ensure that our contrastive generated text has the fewest possible edits with respect to the original text, while also being fluent and close to a human generated contrastive, we resort to a minimal perturbation approach regularized using a BERT language model and attribute classifiers trained on available attributes. We show through qualitative examples and a user study that our method not only conveys more insight because of these attributes, but also leads to better quality (contrastive) text. Quantitatively, we show that our method outperforms other state-of-the-art methods across four data sets on four benchmark metrics.
Code (0)
등록된 구현이 없습니다.
Tasks
AttributeLanguage ModelingLanguage ModellingMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
LLM-Enhanced Energy Contrastive Learning for Out-of-Distribution Detection in Text-Attributed Graphs
Text-attributed graphs, where nodes are enriched with textual attributes, have become a powerful tool for modeling real-world networks such as citation, social, and transaction networks. However, existing methods for lea…
Out-of-Distribution DetectionContrastive LearningNode ClassificationThe Unheard Alternative: Contrastive Explanations for Speech-to-Text Models
Contrastive explanations, which indicate why an AI system produced one output (the target) instead of another (the foil), are widely regarded in explainable AI as more informative and interpretable than standard explanat…
TAGExplainer: Narrating Graph Explanations for Text-Attributed Graph Learning Models
Representation learning of Text-Attributed Graphs (TAGs) has garnered significant attention due to its applications in various domains, including recommendation systems and social networks. Despite advancements in TAG le…
Decision MakingGraph LearningLanguage ModelingLanguage Modelling+4(When) Are Contrastive Explanations of Reinforcement Learning Helpful?
Global explanations of a reinforcement learning (RL) agent's expected behavior can make it safer to deploy. However, such explanations are often difficult to understand because of the complicated nature of many RL polici…
reinforcement-learningReinforcement LearningReinforcement Learning (RL)KACE: Generating Knowledge Aware Contrastive Explanations for Natural Language Inference
In order to better understand the reason behind model behaviors (i.e., making predictions), most recent works have exploited generative models to provide complementary explanations. However, existing approaches in NLP ma…
counterfactualLanguage ModellingNatural Language Inference