paper-with-me

Papers

Explanation Bottleneck Models

2024-09-26 · Shin'ya Yamaguchi, Kosuke Nishida

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/.

📄 PDF Abstract BibTeX arXiv:2409.17663

Code (1)

yshinya6/xbm 공식 구현 pytorch

Tasks

Decoder

Similar Papers 제목 키워드 기반

Self-Explainable Temporal Graph Networks based on Graph Information Bottleneck

2024-06-19 · Sangwoo Seo, Sungwon Kim, Jihyeong Jung, Yoonho Lee 외

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 PredictionPrediction

SurroCBM: Concept Bottleneck Surrogate Models for Generative Post-hoc Explanation

2023-10-11 · Bo Pan, Zhenke Liu, Yifei Zhang, Liang Zhao

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 Making

The Sufficiency-Conciseness Trade-off in LLM Self-Explanation from an Information Bottleneck Perspective

2026-02-15 · Ali Zahedzadeh, Behnam Bahrak arxiv

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 Answering

Explanation Regeneration via Information Bottleneck

2022-12-19 · Qintong Li, Zhiyong Wu, Lingpeng Kong, Wei Bi

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+1

Explaining a black-box using Deep Variational Information Bottleneck Approach

2019-02-19 · Seojin Bang, Pengtao Xie, Heewook Lee, Wei Wu 외

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