CEBaB: Estimating the Causal Effects of Real-World Concepts on NLP Model Behavior

05/27/2022
by   Eldar David Abraham, et al.
4

The increasing size and complexity of modern ML systems has improved their predictive capabilities but made their behavior harder to explain. Many techniques for model explanation have been developed in response, but we lack clear criteria for assessing these techniques. In this paper, we cast model explanation as the causal inference problem of estimating causal effects of real-world concepts on the output behavior of ML models given actual input data. We introduce CEBaB, a new benchmark dataset for assessing concept-based explanation methods in Natural Language Processing (NLP). CEBaB consists of short restaurant reviews with human-generated counterfactual reviews in which an aspect (food, noise, ambiance, service) of the dining experience was modified. Original and counterfactual reviews are annotated with multiply-validated sentiment ratings at the aspect-level and review-level. The rich structure of CEBaB allows us to go beyond input features to study the effects of abstract, real-world concepts on model behavior. We use CEBaB to compare the quality of a range of concept-based explanation methods covering different assumptions and conceptions of the problem, and we seek to establish natural metrics for comparative assessments of these methods.

READ FULL TEXT

page 20

page 24

page 25

page 26

research
05/27/2020

CausaLM: Causal Model Explanation Through Counterfactual Language Models

Understanding predictions made by deep neural networks is notoriously di...
research
09/28/2022

Causal Proxy Models for Concept-Based Model Explanations

Explainability methods for NLP systems encounter a version of the fundam...
research
04/13/2023

counterfactuals: An R Package for Counterfactual Explanation Methods

Counterfactual explanation methods provide information on how feature va...
research
06/07/2022

GRETEL: A unified framework for Graph Counterfactual Explanation Evaluation

Machine Learning (ML) systems are a building part of the modern tools wh...
research
08/24/2020

PermuteAttack: Counterfactual Explanation of Machine Learning Credit Scorecards

This paper is a note on new directions and methodologies for validation ...
research
04/09/2021

Evaluating Explanations for Reading Comprehension with Realistic Counterfactuals

Token-level attributions have been extensively studied to explain model ...

Please sign up or login with your details

Forgot password? Click here to reset