Abstract
Language models (LMs), despite their advances, often depend on spurious correlations, undermining their accuracy and generalizability. This study addresses the overlooked impact of subtler, more complex shortcuts that compromise model reliability beyond oversimplified shortcuts. We introduce a comprehensive benchmark that categorizes shortcuts into occurrence, style, and concept, aiming to explore the nuanced ways in which these shortcuts influence the performance of LMs. Through extensive experiments across traditional LMs, large language models, and state-of-the-art robust models, our research systematically investigates models’ resilience and susceptibilities to sophisticated shortcuts. Our benchmark and code can be found at: https://github.com/yuqing-zhou/shortcut-learning-in-text-classification.- Anthology ID:
- 2024.findings-emnlp.146
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2024
- Month:
- November
- Year:
- 2024
- Address:
- Miami, Florida, USA
- Editors:
- Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 2586–2614
- Language:
- URL:
- https://aclanthology.org/2024.findings-emnlp.146
- DOI:
- 10.18653/v1/2024.findings-emnlp.146
- Cite (ACL):
- Yuqing Zhou, Ruixiang Tang, Ziyu Yao, and Ziwei Zhu. 2024. Navigating the Shortcut Maze: A Comprehensive Analysis of Shortcut Learning in Text Classification by Language Models. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 2586–2614, Miami, Florida, USA. Association for Computational Linguistics.
- Cite (Informal):
- Navigating the Shortcut Maze: A Comprehensive Analysis of Shortcut Learning in Text Classification by Language Models (Zhou et al., Findings 2024)
- PDF:
- https://preview.aclanthology.org/dois-2013-emnlp/2024.findings-emnlp.146.pdf