Trick Me If You Can: Human-in-the-Loop Generation of Adversarial Examples for Question Answering
Open accessThe DOI matches its Crossref record; 14 of the 14 references it cites were found in a registry or an index.
Abstract
Adversarial evaluation stress-tests a model’s understanding of natural language. Because past approaches expose superficial patterns, the resulting adversarial examples are limited in complexity and diversity. We propose human- in-the-loop adversarial generation, where human authors are guided to break models. We aid the authors with interpretations of model predictions through an interactive user interface. We apply this generation framework to a question answering task called Quizbowl, where trivia enthusiasts craft adversarial questions. The resulting questions are validated via live human–computer matches: Although the questions appear ordinary to humans, they systematically stump neural and information retrieval models. The adversarial questions cover diverse phenomena from multi-hop reasoning to entity type distractors, exposing open challenges in robust question answering.
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. (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
SQuAD: 100,000+ Questions for Machine Comprehension of Text
Rajpurkar, P., Zhang, J., Lopyrev, K., & Liang, P. (2016) · Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d16-1264 · Cited by 6,208 · cited 1×
“ng systems. 1 Introduction Proponents of modern machine learning systems have claimed human parity on difficult tasks such as question answering (Yu et al., 2018). Datasets such as SQuAD and TriviaQA (Rajpurkar et al., 2016; Joshi et al., 2017) certainly advanced the state of the art, but do they provide the right exam…”
BackgroundDeep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
Simonyan, K., Vedaldi, A., & Zisserman, A. (2013) · arXiv · doi:10.48550/arxiv.1312.6034 · Cited by 5,370 · cited 1×
“We focus on gradient-based approximations (Simonyan et al., 2014; Montavon et al., 2018) for their computational efficiency.”
Methods for interpreting and understanding deep neural networks
Montavon, G., Samek, W., & Müller, K.-R. (2018) · Digital Signal Processing · doi:10.1016/j.dsp.2017.10.011 · Cited by 2,665
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
TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension
Joshi, M., Choi, E., Weld, D., & Zettlemoyer, L. (2017) · Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p17-1147 · Cited by 1,690
TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension
Joshi, M., Choi, E., Weld, D. S., & Zettlemoyer, L. (2017) · arXiv · doi:10.48550/arxiv.1705.03551 · Cited by 1,650
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 4×
“Thus, recent work stress tests models via adversarial evaluation: elucidating a system’s capabilities by exploiting its weaknesses (Jia and Liang, 2017; Belinkov and Glass, 2019).”
BackgroundInfluentialAnnotation Artifacts in Natural Language Inference Data
Gururangan, S., Swayamdipta, S., Levy, O., Schwartz, R., Bowman, S., & Smith, N. A. (2018) · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers) · doi:10.18653/v1/n18-2017 · Cited by 907
SQuAD: 100,000+ Questions for Machine Comprehension of Text
Rajpurkar, P., Zhang, J., Lopyrev, K., & Liang, P. (2016) · arXiv · doi:10.48550/arxiv.1606.05250 · Cited by 678
Cited by
Pre-trained models: Past, present and future
Han, X., Zhang, Z., Ding, N., Gu, Y., Liu, X., Huo, Y., Qiu, J., Yao, Y., Zhang, A., Zhang, L., et al. (2021) · AI Open · doi:10.1016/j.aiopen.2021.08.002 · Cited by 994
A survey of human-in-the-loop for machine learning
Wu, X., Xiao, L., Sun, Y., Zhang, J., Ma, T., & He, L. (2022) · Future Generation Computer Systems · doi:10.1016/j.future.2022.05.014 · Cited by 800
“[56] developed an open application system that contains an interactive interface to talk with the machine, thereby generating more Q&A language materials to collect more research data and help the researcher explain the model predictions.”
BackgroundMethodInfluentialAdversarial NLI: A New Benchmark for Natural Language Understanding
Nie, Y., Williams, A., Dinan, E., Bansal, M., Weston, J., & Kiela, D. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.441 · Cited by 656
Universal Adversarial Triggers for Attacking and Analyzing NLP
Wallace, E., Feng, S., Kandpal, N., Gardner, M., & Singh, S. (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/d19-1221 · Cited by 642
Self-citationA comprehensive survey on pretrained foundation models: a history from BERT to ChatGPT
Zhou, C., Li, Q., Li, C., Yu, J., Liu, Y., Wang, G., Zhang, K., Ji, C., Yan, Q., He, L., et al. (2025) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-024-02443-6 · Cited by 557
Evaluating 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-citationMeasure 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
Evaluation Examples are not Equally Informative: How should that change NLP Leaderboards?
Rodriguez, P., Barrow, J., Hoyle, A. M., Lalor, J. P., Jia, R., & Boyd-Graber, J. (2021) · Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · doi:10.18653/v1/2021.acl-long.346 · Cited by 47
Self-citationIt Takes Two to Lie: One to Lie, and One to Listen
Peskov, D., Cheng, B., Elgohary, A., Barrow, J., Danescu-Niculescu-Mizil, C., & Boyd-Graber, J. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.353 · Cited by 30
“Beyond playing against humans, playing with a human in the loop ( HITL ) resembles designs for cybersecurity threats (Cranor, 2008), annotation (Branson et al., 2010), and language alteration (Wallace et al., 2019).”
BackgroundSelf-citationHuman in the AI Loop via xAI and Active Learning for Visual Inspection
Rožanec, J. M., Montini, E., Cutrona, V., Papamartzivanos, D., Klemenčič, T., Fortuna, B., Mladenić, D., Veliou, E., Giannetsos, T., & Emmanouilidis, C. (2024) · Artificial Intelligence in Manufacturing · doi:10.1007/978-3-031-46452-2_22 · Cited by 17
Exploring The Landscape of Distributional Robustness for Question Answering Models
Awadalla, A., Wortsman, M., Ilharco, G., Min, S., Magnusson, I., Hajishirzi, H., & Schmidt, L. (2022) · arXiv · doi:10.48550/arxiv.2210.12517 · Cited by 6
Nano: Nested Human-in-the-Loop Reward Learning for Few-shot Language Model Control
Fan, X., Lyu, Y., Liang, P. P., Salakhutdinov, R., & Morency, L.-P. (2023) · Findings of the Association for Computational Linguistics: ACL 2023 · doi:10.18653/v1/2023.findings-acl.758 · Cited by 3
“, 2019), dialog and question answering (Hancock et al., 2019; Wallace et al., 2019), and sentiment analysis (Liu et al.”
BackgroundXian, R. P., Lee, A. J., Lolla, S., Wang, V., Cui, Q., Ro, R., & Abbasi-Asl, R. (2024) · arXiv · doi:10.48550/arxiv.2402.10527
Metadata
- Authors
- Wallace, E., Rodriguez, P., Feng, S., Yamada, I., & Boyd-Graber, J.
- Venue
- Transactions of the Association for Computational Linguistics
- Publisher
- MIT Press - Journals
- Published
- 2019-11
- Volume
- 7
- Pages
- 387-401
- ISSN
- 2307-387X (ISSN-L)
- OpenAlex
- W2946140580
- Cited by
- 129
- References
- 14
- FWCI
- 8.17
- Type
- journal article
- Language
- en
- Open access
- diamond
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
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.