Explanation Bottleneck Models
Recent concept-based interpretable models have succeeded in providing meaningful explanations by pre-defined concept sets. However, the dependency on the pre-defined concepts restricts the application because of the limited number of concepts for explanations. This paper proposes a novel interpretable deep neural network called explanation bottleneck models (XBMs). XBMs generate a text explanation from the input without pre-defined concepts and then predict a final task prediction based on the generated explanation by leveraging pre-trained vision-language encoder-decoder models. To achieve both the target task performance and the explanation quality, we train XBMs through the target task loss with the regularization penalizing the explanation decoder via the distillation from the frozen pre-trained decoder. Our experiments, including a comparison to state-of-the-art concept bottleneck models, confirm that XBMs provide accurate and fluent natural language explanations without pre-defined concept sets. Code will be available at https://github.com/yshinya6/xbm/.
Code (1)
Tasks
DecoderSimilar Papers 제목 키워드 기반
Self-Explainable Temporal Graph Networks based on Graph Information Bottleneck
Temporal Graph Neural Networks (TGNN) have the ability to capture both the graph topology and dynamic dependencies of interactions within a graph over time. There has been a growing need to explain the predictions of TGN…
Link PredictionPredictionSurroCBM: Concept Bottleneck Surrogate Models for Generative Post-hoc Explanation
Explainable AI seeks to bring light to the decision-making processes of black-box models. Traditional saliency-based methods, while highlighting influential data segments, often lack semantic understanding. Recent advanc…
Decision MakingThe Sufficiency-Conciseness Trade-off in LLM Self-Explanation from an Information Bottleneck Perspective
Large Language Models increasingly rely on self-explanations, such as chain of thought reasoning, to improve performance on multi step question answering. While these explanations enhance accuracy, they are often verbose…
Question AnsweringExplanation Regeneration via Information Bottleneck
Explaining the black-box predictions of NLP models naturally and accurately is an important open problem in natural language generation. These free-text explanations are expected to contain sufficient and carefully-selec…
Explanation GenerationLanguage ModelingLanguage ModellingPrompt Engineering+1Explaining a black-box using Deep Variational Information Bottleneck Approach
Interpretable machine learning has gained much attention recently. Briefness and comprehensiveness are necessary in order to provide a large amount of information concisely when explaining a black-box decision system. Ho…
BIG-bench Machine LearningInterpretable Machine Learning