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

Dong-Ho Lee, Akshen Kadakia, Brihi Joshi, Aaron Chan, Ziyi Liu, Kiran Narahari, Takashi Shibuya, Ryosuke Mitani, Toshiyuki Sekiya, Jay Pujara, Xiang Ren


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, thenusing 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 explanationsalign 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%.
Anthology ID:
2023.acl-demo.25
Volume:
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Danushka Bollegala, Ruihong Huang, Alan Ritter
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
264–273
Language:
URL:
https://aclanthology.org/2023.acl-demo.25
DOI:
10.18653/v1/2023.acl-demo.25
Bibkey:
Cite (ACL):
Dong-Ho Lee, Akshen Kadakia, Brihi Joshi, Aaron Chan, Ziyi Liu, Kiran Narahari, Takashi Shibuya, Ryosuke Mitani, Toshiyuki Sekiya, Jay Pujara, and Xiang Ren. 2023. XMD: An End-to-End Framework for Interactive Explanation-Based Debugging of NLP Models. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations), pages 264–273, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
XMD: An End-to-End Framework for Interactive Explanation-Based Debugging of NLP Models (Lee et al., ACL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.acl-demo.25.pdf
Video:
 https://aclanthology.org/2023.acl-demo.25.mp4