INTERACTION: A Generative XAI Framework for Natural Language Inference Explanations
This addresses the need for more diverse explanations in XAI for NLP to account for varied human perspectives, though it is incremental as it builds on existing Transformer-based approaches.
The paper tackles the problem of generating diverse human-readable explanations for natural language inference by proposing INTERACTION, a two-step generative XAI framework that first predicts labels with explanations and then generates multiple diverse explanations. The method achieves up to 4.7% gain in BLEU for explanation generation and up to 4.4% gain in accuracy for prediction on the e-SNLI dataset.
XAI with natural language processing aims to produce human-readable explanations as evidence for AI decision-making, which addresses explainability and transparency. However, from an HCI perspective, the current approaches only focus on delivering a single explanation, which fails to account for the diversity of human thoughts and experiences in language. This paper thus addresses this gap, by proposing a generative XAI framework, INTERACTION (explaIn aNd predicT thEn queRy with contextuAl CondiTional varIational autO-eNcoder). Our novel framework presents explanation in two steps: (step one) Explanation and Label Prediction; and (step two) Diverse Evidence Generation. We conduct intensive experiments with the Transformer architecture on a benchmark dataset, e-SNLI. Our method achieves competitive or better performance against state-of-the-art baseline models on explanation generation (up to 4.7% gain in BLEU) and prediction (up to 4.4% gain in accuracy) in step one; it can also generate multiple diverse explanations in step two.