More Bang for Your Buck: Natural Perturbation for Robust Question Answering
Open accessThe DOI matches its Crossref record; 9 of the 9 references it cites were found in a registry or an index.
Abstract
Deep learning models for linguistic tasks require large training datasets, which are expensive to create.As an alternative to the traditional approach of creating new instances by repeating the process of creating one instance, we propose doing so by first collecting a set of seed examples and then applying humandriven natural perturbations (as opposed to rule-based machine perturbations), which often change the gold label as well.Such perturbations have the advantage of being relatively easier (and hence cheaper) to create than writing out completely new examples.Further, they help address the issue that even models achieving human-level scores on NLP datasets are known to be considerably sensitive to small changes in input.To evaluate the idea, we consider a recent question-answering dataset (BOOLQ) and study our approach as a function of the perturbation cost ratio, the relative cost of perturbing an existing question vs. creating a new one from scratch.We find that when natural perturbations are moderately cheaper to create (cost ratio under 60%), it is more effective to use them for training BOOLQ models: such models exhibit 9% higher robustness and 4.5% stronger generalization, while retaining performance on the original BOOLQ dataset.
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
A large annotated corpus for learning natural language inference
Bowman, S. R., Angeli, G., Potts, C., & Manning, C. D. (2015) · Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d15-1075 · Cited by 3,377 · cited 1×
“While many datasets (Bowman et al., 2015; Rajpurkar et al., 2016) targeting different linguistic tasks have been proposed, nearly all are created by repeating a fixed process used for writing a single example.”
Natural Questions: A benchmark for question answering research
Kwiatkowski, T., Palomaki, J., Redfield, O., Collins, M., Parikh, A., Alberti, C., Epstein, D., Polosukhin, I., Devlin, J., Lee, K., et al. (2019) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00276 · Cited by 2,069
Adversarial Examples for Evaluating Reading Comprehension Systems
Jia, R., & Liang, P. (2017) · Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d17-1215 · Cited by 1,410 · cited 2×
“An inspiration for our approach is the lack of robustness of current state-of-the-art models to minor adversarial changes in the input (Jia and Liang, 2017).”
BackgroundSuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems
Wang, A., Pruksachatkun, Y., Nangia, N., Singh, A., Michael, J., Hill, F., Levy, O., & Bowman, S. R. (2019) · arXiv · doi:10.48550/arxiv.1905.00537 · Cited by 1,051
Looking Beyond the Surface: A Challenge Set for Reading Comprehension over Multiple Sentences
Khashabi, D., Chaturvedi, S., Roth, M., Upadhyay, S., & Roth, D. (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/n18-1023 · Cited by 683
Self-citationWinoGrande: An Adversarial Winograd Schema Challenge at Scale
Sakaguchi, K., Le Bras, R., Bhagavatula, C., & Choi, Y. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i05.6399 · Cited by 579
Breaking NLI Systems with Sentences that Require Simple Lexical Inferences
Glockner, M., Shwartz, V., & Goldberg, Y. (2018) · Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) · doi:10.18653/v1/p18-2103 · Cited by 319 · cited 1×
“A closely relevant line of work is adversarial perturbations to expose the weaknesses of systems upon local changes and criticize their lack robustness (Ebrahimi et al., 2018; Glockner et al., 2018; Dinan et al., 2019).”
BackgroundGeva, M., Goldberg, Y., & Berant, J. (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/d19-1107 · Cited by 284 · cited 1×
“(c) It should incentivize creativity and diversity in local perturbations by, for instance, showing thought-provoking suggestions, using a diverse pool of annotators (Geva et al., 2019), etc.”
BackgroundBuild it Break it Fix it for Dialogue Safety: Robustness from Adversarial Human Attack
Dinan, E., Humeau, S., Chintagunta, B., & Weston, J. (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/d19-1461 · Cited by 161 · cited 2×
“A closely relevant line of work is adversarial perturbations to expose the weaknesses of systems upon local changes and criticize their lack robustness (Ebrahimi et al., 2018; Glockner et al., 2018; Dinan et al., 2019).”
Background
Cited by
UNIFIEDQA: Crossing Format Boundaries with a Single QA System
Khashabi, D., Min, S., Khot, T., Sabharwal, A., Tafjord, O., Clark, P., & Hajishirzi, H. (2020) · Findings of the Association for Computational Linguistics: EMNLP 2020 · doi:10.18653/v1/2020.findings-emnlp.171 · Cited by 514
Self-citationEvaluating Models’ Local Decision Boundaries via Contrast Sets
Gardner, M., Artzi, Y., Basmov, V., Berant, J., Bogin, B., Chen, S., Dasigi, P., Dua, D., Elazar, Y., Gottumukkala, A., et al. (2020) · Findings of the Association for Computational Linguistics: EMNLP 2020 · doi:10.18653/v1/2020.findings-emnlp.117 · Cited by 256
Self-citationTowards a Unified Multi-Dimensional Evaluator for Text Generation
Zhong, M., Liu, Y., Yin, D., Mao, Y., Jiao, Y., Liu, P., Zhu, C., Ji, H., & Han, J. (2022) · Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2022.emnlp-main.131 · Cited by 117
Measure and Improve Robustness in NLP Models: A Survey
Wang, X., Wang, H., & Yang, D. (2022) · Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · doi:10.18653/v1/2022.naacl-main.339 · Cited by 90
Brittlebench: Quantifying LLM robustness via prompt sensitivity
Romanou, A., Ibrahim, M., Ross, C., Oktar, K., Shaib, C., Bell, S. J., Ovalle, A., Bosselut, A., Dodge, J., Sinha, K., et al. (2026) · arXiv · doi:10.48550/arxiv.2603.13285 · Cited by 24
“Our results challenge this scaling hypothesis, showing that frontier models exhibit prompt sensitivity qualitatively similar to that of smaller open-weight models.”
Metadata
- Authors
- Khashabi, D., Khot, T., & Sabharwal, A.
- Venue
- Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
- Published
- 2020
- Pages
- 163-170
- OpenAlex
- W3092399494
- Cited by
- 56
- References
- 9
- FWCI
- 5.24
- 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: More Bang for Your Buck: Natural Perturbation for Robust Question Answering. https://app.cochat.ai/papers/10.18653/v1/2020.emnlp-main.12
- The paper
- Khashabi, D., Khot, T., & Sabharwal, A. (2020). More Bang for Your Buck: Natural Perturbation for Robust Question Answering. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). https://doi.org/10.18653/v1/2020.emnlp-main.12
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.