XMD: An End-to-End Framework for Interactive Explanation-Based Debugging of NLP Models

TL;DR

XMD is an open-source, end-to-end framework that enables interactive explanation-based debugging of NLP models, allowing users to provide feedback and automatically update models to improve out-of-distribution performance.

Contribution

It introduces XMD, the first comprehensive framework for explanation-based debugging of NLP models with real-time updates and user-friendly interface.

Findings

Improves OOD performance by up to 18%

Provides an open-source, deployable debugging tool

Enables real-time model updates based on user feedback

Abstract

NLP models are susceptible to learning spurious biases (i.e., bugs) that work on some datasets but do not properly reflect the underlying task. Explanation-based model debugging aims to resolve spurious biases by showing human users explanations of model behavior, asking users to give feedback on the behavior, then using the feedback to update the model. While existing model debugging methods have shown promise, their prototype-level implementations provide limited practical utility. Thus, we propose XMD: the first open-source, end-to-end framework for explanation-based model debugging. Given task- or instance-level explanations, users can flexibly provide various forms of feedback via an intuitive, web-based UI. After receiving user feedback, XMD automatically updates the model in real time, by regularizing the model so that its explanations align with the user feedback. The new model can then be easily deployed into real-world applications via Hugging Face. Using XMD, we can improve the model's OOD performance on text classification tasks by up to 18%.