Evaluating the Robustness of Neural Language Models to Input Perturbations
Open accessThe DOI matches its Crossref record; 13 of the 13 references it cites were found in a registry or an index.
Abstract
High-performance neural language models have obtained state-of-the-art results on a wide range of Natural Language Processing (NLP) tasks.However, results for common benchmark datasets often do not reflect model reliability and robustness when applied to noisy, real-world data.In this study, we design and implement various types of character-level and wordlevel perturbation methods to simulate realistic scenarios in which input texts may be slightly noisy or different from the data distribution on which NLP systems were trained.Conducting comprehensive experiments on different NLP tasks, we investigate the ability of high-performance language models such as BERT, XLNet, RoBERTa, and ELMo in handling different types of input perturbations.The results suggest that language models are sensitive to input perturbations and their performance can decrease even when small changes are introduced.We highlight that models need to be further improved and that current benchmarks are not reflecting model robustness well.We argue that evaluations on perturbed inputs should routinely complement widely-used benchmarks in order to yield a more realistic understanding of NLP systems' robustness.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325 · cited 2×
“High-performance deep neural language models such as BERT (Devlin et al., 2018), XLNet (Z. testing in software engineering.”
BackgroundMethodSentence-BERT: Sentence Embeddings using Siamese BERT-Networks
Reimers, N., & Gurevych, I. (2019) · Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · doi:10.18653/v1/d19-1410 · Cited by 12,778 · cited 1×
“Sentence encoders such as InferSent (Conneau et al., 2017), Universal Sentence Encoder (Cer et al., 2018), and BERT trained for semantic similarity (Reimers and Gurevych, 2019) can be used to give users clues how semantically similar the original and perturbed sentences are.”
MethodDeep Contextualized Word Representations
Peters, M., Neumann, M., Iyyer, M., Gardner, M., Clark, C., Lee, K., & Zettlemoyer, L. (2018) · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers) · doi:10.18653/v1/n18-1202 · Cited by 11,983
Transformers: State-of-the-Art Natural Language Processing
Wolf, T., Debut, L., Sanh, V., Chaumond, J., Delangue, C., Moi, A., Cistac, P., Rault, T., Louf, R., Funtowicz, M., et al. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations · doi:10.18653/v1/2020.emnlp-demos.6 · Cited by 8,741
Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank
Socher, R., Perelygin, A., Wu, J., Chuang, J., Manning, C. D., Ng, A., & Potts, C. (2013) · Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d13-1170 · Cited by 6,878
XLNet: Generalized Autoregressive Pretraining for Language Understanding
Yang, Z., Dai, Z., Yang, Y., Carbonell, J., Salakhutdinov, R., & Le, Q. V. (2019) · arXiv · doi:10.48550/arxiv.1906.08237 · Cited by 6,687
Supervised Learning of Universal Sentence Representations from Natural Language Inference Data
Conneau, A., Kiela, D., Schwenk, H., Barrault, L., & Bordes, A. (2017) · Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d17-1070 · Cited by 2,049 · cited 1×
“Sentence encoders such as InferSent (Conneau et al., 2017), Universal Sentence Encoder (Cer et al., 2018), and BERT trained for semantic similarity (Reimers and Gurevych, 2019) can be used to give users clues how semantically similar the original and perturbed sentences are.”
MethodSemEval-2017 Task 1: Semantic Textual Similarity Multilingual and Crosslingual Focused Evaluation
Cer, D., Diab, M., Agirre, E., Lopez-Gazpio, I., & Specia, L. (2017) · Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017) · doi:10.18653/v1/s17-2001 · Cited by 1,562 · cited 1×
“Stanford Sentiment Treebank (SST) (Socher et al., 2013) STS benchmark (Cer et al., 2017) is a Semantic Similarity (SS) dataset comprising of more than 8K text pairs extracted from image captions, news headlines, and user forums.”
BackgroundCer, D., Yang, Y., Kong, S.-Y., Hua, N., Limtiaco, N., John, R. S., Constant, N., Guajardo-Cespedes, M., Yuan, S., Tar, C., et al. (2018) · arXiv · doi:10.48550/arxiv.1803.11175 · Cited by 1,267 · cited 1×
“Sentence encoders such as InferSent (Conneau et al., 2017), Universal Sentence Encoder (Cer et al., 2018), and BERT trained for semantic similarity (Reimers and Gurevych, 2019) can be used to give users clues how semantically similar the original and perturbed sentences are.”
Method
Cited by
The Fallacy of AI Functionality
Raji, I. D., Kumar, I. E., Horowitz, A., & Selbst, A. (2022) · 2022 ACM Conference on Fairness Accountability and Transparency · doi:10.1145/3531146.3533158 · Cited by 251
Repairing the Cracked Foundation: A Survey of Obstacles in Evaluation Practices for Generated Text
Gehrmann, S., Clark, E., & Sellam, T. (2023) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1.13715 · Cited by 123
Prompt Injection attack against LLM-integrated Applications
Liu, Y., Deng, G., Li, Y., Wang, K., Wang, Z., Wang, X., Zhang, T., Liu, Y., Wang, H., Zheng, Y., et al. (2023) · arXiv · doi:10.48550/arxiv.2306.05499 · Cited by 100
Promptbreeder: Self-Referential Self-Improvement via Prompt Evolution
Fernando, C., Banarse, D., Michalewski, H., Osindero, S., & Rocktäschel, T. (2023) · arXiv · doi:10.48550/arxiv.2309.16797 · Cited by 31
Influence of External Information on Large Language Models Mirrors Social Cognitive Patterns
Bian, N., Lin, H., Liu, P., Lu, Y., Zhang, C., He, B., Han, X., & Sun, L. (2023) · arXiv · doi:10.48550/arxiv.2305.04812 · Cited by 24
Metadata
- Authors
- Moradi, M., & Samwald, M.
- Venue
- Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
- Published
- 2021
- Pages
- 1558-1570
- OpenAlex
- W3198690080
- Cited by
- 69
- References
- 13
- FWCI
- 5.43
- Type
- conference paper
- Language
- en
- Open access
- hybrid
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Evaluating the Robustness of Neural Language Models to Input Perturbations. https://app.cochat.ai/papers/10.18653/v1/2021.emnlp-main.117
- The paper
- Moradi, M., & Samwald, M. (2021). Evaluating the Robustness of Neural Language Models to Input Perturbations. Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. https://doi.org/10.18653/v1/2021.emnlp-main.117
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.