The DOI matches its Crossref record; 38 of the 38 references it cites were found in a registry or an index.
Post-hoc Interpretability for Neural NLP: A Survey
Open accessAbstract
Neural networks for NLP are becoming increasingly complex and widespread, and there is a growing concern if these models are responsible to use. Explaining models helps to address the safety and ethical concerns and is essential for accountability. Interpretability serves to provide these explanations in terms that are understandable to humans. Additionally, post-hoc methods provide explanations after a model is learned and are generally model-agnostic. This survey provides a categorization of how recent post-hoc interpretability methods communicate explanations to humans, it discusses each method in-depth, and how they are validated, as the latter is often a common concern.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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
Efficient Estimation of Word Representations in Vector Space
Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013) · arXiv · doi:10.48550/arxiv.1301.3781 · Cited by 26,568
A Unified Approach to Interpreting Model Predictions
Lundberg, S., & Lee, S.-I. (2017) · arXiv · doi:10.48550/arxiv.1705.07874 · Cited by 23,707
BLEU: a method for automatic evaluation of machine translation
Papineni, K., Roukos, S., Ward, T., & Zhu, W.-J. (2001) · Proceedings of the 40th Annual Meeting on Association for Computational Linguistics - ACL '02 · doi:10.3115/1073083.1073135 · Cited by 21,344
Neural Machine Translation by Jointly Learning to Align and Translate
Bahdanau, D., Cho, K., & Bengio, Y. (2014) · arXiv · doi:10.48550/arxiv.1409.0473 · Cited by 16,213
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., & Liu, P. J. (2019) · arXiv · doi:10.48550/arxiv.1910.10683 · Cited by 10,929
Rudin, C. (2019) · Nature Machine Intelligence · doi:10.1038/s42256-019-0048-x · Cited by 10,561
Costello, A. B., & Osborne, J. (2005) · University of Massachusetts Amherst · doi:10.7275/jyj1-4868 · Cited by 10,297
Scaling Laws for Neural Language Models
Kaplan, J., McCandlish, S., Henighan, T., Brown, T. B., Chess, B., Child, R., Gray, S., Radford, A., Wu, J., & Amodei, D. (2020) · arXiv · doi:10.48550/arxiv.2001.08361 · Cited by 9,550 · cited 1×
“This increase of model complexity is motivated by a general correlation between model size and test performance [14, 43].”
BackgroundTransformers: 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
Dissecting racial bias in an algorithm used to manage the health of populations
Obermeyer, Z., Powers, B., Vogeli, C., & Mullainathan, S. (2019) · Science · doi:10.1126/science.aax2342 · Cited by 7,137 · cited 1×
“For many of these applications, neural models have been shown to exhibit unwanted biases and similar ethical issues [16, 20, 42, 75, 82, 100].”
BackgroundOn the Dangers of Stochastic Parrots: Can Language Models Be Too Big? 🦜
Bender, E. M., Gebru, T., McMillan-Major, A., & Shmitchell, S. (2021) · Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency · doi:10.1145/3442188.3445922 · Cited by 6,988 · cited 1×
“For many of these applications, neural models have been shown to exhibit unwanted biases and similar ethical issues [16, 20, 42, 75, 82, 100].”
BackgroundPeeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI)
Adadi, A., & Berrada, M. (2018) · IEEE Access · doi:10.1109/access.2018.2870052 · Cited by 6,294
Lipton, Z. C. (2018) · Queue · doi:10.1145/3236386.3241340 · Cited by 5,427
Explanation in artificial intelligence: Insights from the social sciences
Miller, T. (2019) · Artificial Intelligence · doi:10.1016/j.artint.2018.07.007 · Cited by 5,302
A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference
Williams, A., Nangia, N., & Bowman, S. (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/n18-1101 · Cited by 3,342
A Survey on Explainable Artificial Intelligence (XAI): Toward Medical XAI
Tjoa, E., & Guan, C. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2020.3027314 · Cited by 2,524
Anchors: High-Precision Model-Agnostic Explanations
Ribeiro, M. T., Singh, S., & Guestrin, C. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11491 · Cited by 2,162 · cited 2×
“…the case of the gradient-based methods or LIME , the Anchors simply provides a shortlist of words that were most relevant for making the prediction [95]. neg we never feel anything for these characters 0.95 neg The authors show human-groundedness with a similar user setup as in LIME [94]. neg…”
BackgroundMethodInfluentialMachine Learning Interpretability: A Survey on Methods and Metrics
Carvalho, D. V., Pereira, E. M., & Cardoso, J. S. (2019) · Electronics · doi:10.3390/electronics8080832 · Cited by 1,842
Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings
Bolukbasi, T., Chang, K.-W., Zou, J., Saligrama, V., & Kalai, A. (2016) · arXiv · doi:10.48550/arxiv.1607.06520 · Cited by 1,615
A primer in BERTology: What we know about how BERT works
Rogers, A., Kovaleva, O., & Rumshisky, A. (2020) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00349 · Cited by 1,552
Understanding Black-box Predictions via Influence Functions
Koh, P. W., & Liang, P. (2017) · arXiv · doi:10.48550/arxiv.1703.04730 · Cited by 1,514
BERT Rediscovers the Classical NLP Pipeline
Tenney, I., Das, D., & Pavlick, E. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1452 · Cited by 1,307
Kim, B., Wattenberg, M., Gilmer, J., Cai, C., Wexler, J., Viegas, F., & Sayres, R. (2017) · arXiv · doi:10.48550/arxiv.1711.11279 · Cited by 1,240
Quantifying Attention Flow in Transformers
Abnar, S., & Zuidema, W. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.385 · Cited by 995
Rationalizing Neural Predictions
Lei, T., Barzilay, R., & Jaakkola, T. (2016) · Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d16-1011 · Cited by 777
Serrano, S., & Smith, N. A. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1282 · Cited by 690
WinoGrande: 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
Accountability of AI Under the Law: The Role of Explanation
Doshi-Velez, F., Kortz, M., Budish, R., Bavitz, C., Gershman, S. J., O'Brien, D., Scott, K., Shieber, S., Waldo, J., Weinberger, D., et al. (2017) · doi:10.2139/ssrn.3064761 · Cited by 457 · cited 5×
“For example, if a predictive mistake happens which caused harm, it is important to explain why this mistake happened [38].”
BackgroundInfluentialDesigning and Interpreting Probes with Control Tasks
Hewitt, J., & Liang, P. (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/d19-1275 · Cited by 393
Towards Automatic Concept-based Explanations
Ghorbani, A., Wexler, J., Zou, J., & Kim, B. (2019) · arXiv · doi:10.48550/arxiv.1902.03129 · Cited by 378
e-SNLI: Natural language inference with natural language explanations
Camburu, O.-M., Rocktäschel, T., Lukasiewicz, T., & Blunsom, P. (2018) · arXiv · doi:10.48550/arxiv.1812.01193 · Cited by 367 · cited 1×
“…for these While those methods are often quite general, they are not discussed in this survey which focuses on post-hoc methods. the year 's best and most unpredictable comedy The idea is that by enforcing the model to reason about its behavior, the model can generalize better [23, 63–65, 69, 92].”
BackgroundPerturbation-Based Explanations of Prediction Models
Robnik-Šikonja, M., & Bohanec, M. (2018) · Human–Computer Interaction Series · doi:10.1007/978-3-319-90403-0_9 · Cited by 171
Did the Model Understand the Question?
Mudrakarta, P. K., Taly, A., Sundararajan, M., & Dhamdhere, K. (2018) · Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p18-1176 · Cited by 166
Tenney, I., Wexler, J., Bastings, J., Bolukbasi, T., Coenen, A., Gehrmann, S., Jiang, E., Pushkarna, M., Radebaugh, C., Reif, E., et al. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations · doi:10.18653/v1/2020.emnlp-demos.15 · Cited by 138 · cited 1×
“We suspect a reason for primarily explaining sequence-to-class models, is that sequence-to-sequence explanations may depend on interactive visualization to a greater extent [72, 111, 117], which is harder to implement and write about in typical machine learning venues.”
BackgroundGarrido-Muñoz, I., Montejo-Ráez, A., Martínez-Santiago, F., & Ureña-López, L. A. (2021) · Applied Sciences · doi:10.3390/app11073184 · Cited by 123
Hase, P., Zhang, S., Xie, H., & Bansal, M. (2020) · Findings of the Association for Computational Linguistics: EMNLP 2020 · doi:10.18653/v1/2020.findings-emnlp.390 · Cited by 62
How to Explain Individual Classification Decisions
(2010) · Journal of Machine Learning Research · doi:10.5555/1756006.1859912 · Cited by 54
Cited by
Explainable AI (XAI): A systematic meta-survey of current challenges and future opportunities
Saeed, W., & Omlin, C. (2023) · Knowledge-Based Systems · doi:10.1016/j.knosys.2023.110273 · Cited by 783
ŞAHiN, E., Arslan, N. N., & Özdemir, D. (2025) · Neural Computing and Applications · doi:10.1007/s00521-024-10437-2 · Cited by 278
Cascella, M., Semeraro, F., Montomoli, J., Bellini, V., Piazza, O., & Bignami, E. (2024) · Journal of Medical Systems · doi:10.1007/s10916-024-02045-3 · Cited by 219
Understanding the Role of Human Intuition on Reliance in Human-AI Decision-Making with Explanations
Chen, V., Liao, Q. V., Wortman Vaughan, J., & Bansal, G. (2023) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3610219 · Cited by 220
“For the biography classification task, we used a standard approach [58] of color-highlighting the words (features), particularly those with the top 10 highest-magnitude coefficients, as shown in Figure 1 (c).”
MethodXAIR: A Systematic Metareview of Explainable AI (XAI) Aligned to the Software Development Process
Clement, T., Kemmerzell, N., Abdelaal, M., & Amberg, M. (2023) · Machine Learning and Knowledge Extraction · doi:10.3390/make5010006 · Cited by 131
Metadata
- Authors
- Madsen, A., Reddy, S., & Chandar, S.
- Venue
- ACM Computing Surveys
- Published
- 2022-12-23
- Volume
- 55
- Issue
- 8
- Pages
- 1-42
- ISSN
- 0360-0300 (ISSN-L)
- 1557-7341
- OpenAlex
- W3187467055
- Cited by
- 207
- References
- 38
- FWCI
- 14.38
- Type
- journal article
- 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
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.