XMD: An End-to-End Framework for Interactive Explanation-Based Debugging of NLP Models
This addresses the issue of debugging biased NLP models for practitioners, offering a practical tool, though it is incremental as it builds on existing debugging methods.
The paper tackles the problem of NLP models learning spurious biases by proposing XMD, an end-to-end framework for interactive explanation-based debugging that allows users to provide feedback via a web UI to update models in real time, resulting in up to 18% improvement in out-of-distribution performance on text classification tasks.
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%.