Text Counterfactuals via Latent Optimization and Shapley-Guided Search

10/22/2021
by   Quintin Pope, et al.
0

We study the problem of generating counterfactual text for a classifier as a means for understanding and debugging classification. Given a textual input and a classification model, we aim to minimally alter the text to change the model's prediction. White-box approaches have been successfully applied to similar problems in vision where one can directly optimize the continuous input. Optimization-based approaches become difficult in the language domain due to the discrete nature of text. We bypass this issue by directly optimizing in the latent space and leveraging a language model to generate candidate modifications from optimized latent representations. We additionally use Shapley values to estimate the combinatoric effect of multiple changes. We then use these estimates to guide a beam search for the final counterfactual text. We achieve favorable performance compared to recent white-box and black-box baselines using human and automatic evaluations. Ablation studies show that both latent optimization and the use of Shapley values improve success rate and the quality of the generated counterfactuals.

READ FULL TEXT
research
09/14/2023

Text-to-Image Models for Counterfactual Explanations: a Black-Box Approach

This paper addresses the challenge of generating Counterfactual Explanat...
research
06/12/2023

Diffusion Models for Black-Box Optimization

The goal of offline black-box optimization (BBO) is to optimize an expen...
research
09/12/2023

Language Models as Black-Box Optimizers for Vision-Language Models

Vision-language models (VLMs) pre-trained on web-scale datasets have dem...
research
03/25/2021

ECINN: Efficient Counterfactuals from Invertible Neural Networks

Counterfactual examples identify how inputs can be altered to change the...
research
04/24/2023

TIGTEC : Token Importance Guided TExt Counterfactuals

Counterfactual examples explain a prediction by highlighting changes of ...
research
06/30/2021

Improving black-box optimization in VAE latent space using decoder uncertainty

Optimization in the latent space of variational autoencoders is a promis...
research
07/25/2023

Counterfactual Explanation via Search in Gaussian Mixture Distributed Latent Space

Counterfactual Explanations (CEs) are an important tool in Algorithmic R...

Please sign up or login with your details

Forgot password? Click here to reset