AutoCAD: Automatically Generate Counterfactuals for Mitigating Shortcut Learning
Jiaxin Wen, Yeshuang Zhu, Jinchao Zhang, Jie Zhou, Minlie Huang
Abstract
Recent studies have shown the impressive efficacy of counterfactually augmented data (CAD) for reducing NLU models’ reliance on spurious features and improving their generalizability. However, current methods still heavily rely on human efforts or task-specific designs to generate counterfactuals, thereby impeding CAD’s applicability to a broad range of NLU tasks. In this paper, we present AutoCAD, a fully automatic and task-agnostic CAD generation framework. AutoCAD first leverages a classifier to unsupervisedly identify rationales as spans to be intervened, which disentangles spurious and causal features. Then, AutoCAD performs controllable generation enhanced by unlikelihood training to produce diverse counterfactuals. Extensive evaluations on multiple out-of-domain and challenge benchmarks demonstrate that AutoCAD consistently and significantly boosts the out-of-distribution performance of powerful pre-trained models across different NLU tasks, which is comparable or even better than previous state-of-the-art human-in-the-loop or task-specific CAD methods.- Anthology ID:
- 2022.findings-emnlp.170
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2022
- Month:
- December
- Year:
- 2022
- Address:
- Abu Dhabi, United Arab Emirates
- Editors:
- Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 2302–2317
- Language:
- URL:
- https://aclanthology.org/2022.findings-emnlp.170
- DOI:
- 10.18653/v1/2022.findings-emnlp.170
- Cite (ACL):
- Jiaxin Wen, Yeshuang Zhu, Jinchao Zhang, Jie Zhou, and Minlie Huang. 2022. AutoCAD: Automatically Generate Counterfactuals for Mitigating Shortcut Learning. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 2302–2317, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
- Cite (Informal):
- AutoCAD: Automatically Generate Counterfactuals for Mitigating Shortcut Learning (Wen et al., Findings 2022)
- PDF:
- https://preview.aclanthology.org/ingest-2024-clasp/2022.findings-emnlp.170.pdf