KNOW How to Make Up Your Mind! Adversarially Detecting and Alleviating Inconsistencies in Natural Language Explanations
Myeongjun Jang, Bodhisattwa Prasad Majumder, Julian McAuley, Thomas Lukasiewicz, Oana-Maria Camburu
Abstract
While recent works have been considerably improving the quality of the natural language explanations (NLEs) generated by a model to justify its predictions, there is very limited research in detecting and alleviating inconsistencies among generated NLEs. In this work, we leverage external knowledge bases to significantly improve on an existing adversarial attack for detecting inconsistent NLEs. We apply our attack to high-performing NLE models and show that models with higher NLE quality do not necessarily generate fewer inconsistencies. Moreover, we propose an off-the-shelf mitigation method to alleviate inconsistencies by grounding the model into external background knowledge. Our method decreases the inconsistencies of previous high-performing NLE models as detected by our attack.- Anthology ID:
- 2023.acl-short.47
- Volume:
- Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
- Month:
- July
- Year:
- 2023
- Address:
- Toronto, Canada
- Editors:
- Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 540–553
- Language:
- URL:
- https://aclanthology.org/2023.acl-short.47
- DOI:
- 10.18653/v1/2023.acl-short.47
- Cite (ACL):
- Myeongjun Jang, Bodhisattwa Prasad Majumder, Julian McAuley, Thomas Lukasiewicz, and Oana-Maria Camburu. 2023. KNOW How to Make Up Your Mind! Adversarially Detecting and Alleviating Inconsistencies in Natural Language Explanations. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 540–553, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- KNOW How to Make Up Your Mind! Adversarially Detecting and Alleviating Inconsistencies in Natural Language Explanations (Jang et al., ACL 2023)
- PDF:
- https://preview.aclanthology.org/ingest-2024-clasp/2023.acl-short.47.pdf