Papers with feature attribution models
Necessity and Sufficiency for Explaining Text Classifiers: A Case Study in Hate Speech Detection (2022.naacl-main)
Copied to clipboard
| Challenge: | XAI features usually provide a single importance score for each token, but feature attribution methods provide two complementary and theoretically-grounded scores for each utterance. |
| Approach: | They propose a feature attribution method that generates explicit perturbations of the input text, allowing the importance scores themselves to be explainable. |
| Outcome: | The proposed method explain the predictions of hate speech detection models on a set of curated examples from a test suite. |