2000 character limit reached
Discovering Highly Influential Shortcut Reasoning: An Automated Template-Free Approach (2312.09718v1)
Published 15 Dec 2023 in cs.CL
Abstract: Shortcut reasoning is an irrational process of inference, which degrades the robustness of an NLP model. While a number of previous work has tackled the identification of shortcut reasoning, there are still two major limitations: (i) a method for quantifying the severity of the discovered shortcut reasoning is not provided; (ii) certain types of shortcut reasoning may be missed. To address these issues, we propose a novel method for identifying shortcut reasoning. The proposed method quantifies the severity of the shortcut reasoning by leveraging out-of-distribution data and does not make any assumptions about the type of tokens triggering the shortcut reasoning. Our experiments on Natural Language Inference and Sentiment Analysis demonstrate that our framework successfully discovers known and unknown shortcut reasoning in the previous work.
- TweetEval: Unified benchmark and comparative evaluation for tweet classification. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 1644–1650, Online. Association for Computational Linguistics.
- Shortcut learning in deep neural networks. Nature Machine Intelligence, page 665–673.
- Annotation artifacts in natural language inference data. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), pages 107–112, New Orleans, Louisiana. Association for Computational Linguistics.
- Explaining black box predictions and unveiling data artifacts through influence functions. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 5553–5563, Online. Association for Computational Linguistics.
- A survey on measuring and mitigating reasoning shortcuts in machine reading comprehension. Computing Research Repository, arXiv:2209.01824.
- Are all spurious features in natural language alike? an analysis through a causal lens. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 9804–9817, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
- The multilingual Amazon reviews corpus. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 4563–4568, Online. Association for Computational Linguistics.
- Pang Wei Koh and Percy Liang. 2017. Understanding black-box predictions via influence functions. In Proceedings of the 34th International Conference on Machine Learning, page 1885–1894.
- Roberta: A robustly optimized bert pretraining approach. Computing Research Repository, arXiv:1907.11692.
- Right for the wrong reasons: Diagnosing syntactic heuristics in natural language inference. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 3428–3448, Florence, Italy. Association for Computational Linguistics.
- Adversarial NLI: A new benchmark for natural language understanding. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 4885–4901, Online. Association for Computational Linguistics.
- Combining feature and instance attribution to detect artifacts. In Findings of the Association for Computational Linguistics: ACL 2022, pages 1934–1946, Dublin, Ireland. Association for Computational Linguistics.
- Hypothesis only baselines in natural language inference. In Proceedings of the Seventh Joint Conference on Lexical and Computational Semantics, pages 180–191, New Orleans, Louisiana. Association for Computational Linguistics.
- Beyond accuracy: Behavioral testing of NLP models with CheckList. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 4902–4912, Online. Association for Computational Linguistics.
- Beyond leaderboards: A survey of methods for revealing weaknesses in natural language inference data and models. Computing Research Repository, arXiv:2005.14709.
- Axiomatic attribution for deep networks. In Proceedings of the 34th International Conference on Machine Learning, page 3319–3328.
- Identifying and mitigating spurious correlations for improving robustness in NLP models. In Findings of the Association for Computational Linguistics: NAACL 2022, pages 1719–1729, Seattle, United States. Association for Computational Linguistics.
- Measure and improve robustness in NLP models: A survey. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 4569–4586, Seattle, United States. Association for Computational Linguistics.
- A broad-coverage challenge corpus for sentence understanding through inference. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pages 1112–1122, New Orleans, Louisiana. Association for Computational Linguistics.
Sponsor
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.