paper-with-me

Papers

A causal framework for explaining the predictions of black-box sequence-to-sequence models

2017-07-06 · EMNLP 2017 9 · David Alvarez-Melis, Tommi S. Jaakkola

We interpret the predictions of any black-box structured input-structured output model around a specific input-output pair. Our method returns an "explanation" consisting of groups of input-output tokens that are causally related. These dependencies are inferred by querying the black-box model with perturbed inputs, generating a graph over tokens from the responses, and solving a partitioning problem to select the most relevant components. We focus the general approach on sequence-to-sequence problems, adopting a variational autoencoder to yield meaningful input perturbations. We test our method across several NLP sequence generation tasks.

📄 PDF Abstract BibTeX arXiv:1707.01943

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

A Causal Lens for Peeking into Black Box Predictive Models: Predictive Model Interpretation via Causal Attribution

2020-08-01 · Aria Khademi, Vasant Honavar

With the increasing adoption of predictive models trained using machine learning across a wide range of high-stakes applications, e.g., health care, security, criminal justice, finance, and education, there is a growing …

severity prediction

CMA-R:Causal Mediation Analysis for Explaining Rumour Detection

2024-02-13 · Lin Tian, Xiuzhen Zhang, Jey Han Lau

We apply causal mediation analysis to explain the decision-making process of neural models for rumour detection on Twitter. Interventions at the input and network level reveal the causal impacts of tweets and words in th…

Decision MakingRumour Detection

Explaining the Behavior of Black-Box Prediction Algorithms with Causal Learning

2020-06-03 · Numair Sani, Daniel Malinsky, Ilya Shpitser

Causal approaches to post-hoc explainability for black-box prediction models (e.g., deep neural networks trained on image pixel data) have become increasingly popular. However, existing approaches have two important shor…

counterfactual

TimeSAE: Causal Sparse Decoding for Faithful Explanations of Black-Box Time Series Models

2026-01-14 · Khalid Oublal, Quentin Bouniot, Qi Gan, Stephan Clémençon 외 arxiv

As black box models and pretrained models gain traction in time series applications, understanding and explaining their predictions becomes increasingly vital, especially in high-stakes domains where interpretability and…

CIExplainer++: Generating Causal and Interpretable Explanations for Graph Neural Networks

2026-06-17 · Francisco Caldas, Sahil Satish Kumar, Ruben Belo, Cláudia Soares arxiv

Explainable Artificial Intelligence aims to make black-box models more trustworthy by presenting, in a human-understandable manner, the elements that lead to the model's output. This involves both (i) identifying compone…

Causal Inference