---
title: "Explaining NLP Models via Minimal Contrastive Editing (MiCE)"
description: "The authors propose MiCE, which explains a prediction by rewriting the input just enough that a fixed… 75 references, cited by 68 papers here."
authors: ["Alexis Ross", "Ana Marasović", "Matthew Peters"]
year: 2021
venue: "Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021"
source: "https://aclanthology.org/2021.findings-acl.336/"
doi: "10.18653/v1/2021.findings-acl.336"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/ross-2021-explaining-nlp-models-minimal-contrastive/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/ross-2021-explaining-nlp-models-minimal-contrastive/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2021](https://md.research.elamur.ai/free/en/papers/2021/page/3/) / Explaining NLP Models via Minimal Contrastive Editing (MiCE)

# Explaining NLP Models via Minimal Contrastive Editing (MiCE)

**Authors:** [Alexis Ross](https://md.research.elamur.ai/free/en/authors/alexis-ross/), [Ana Marasović](https://md.research.elamur.ai/free/en/authors/ana-marasovic/) and [Matthew Peters](https://md.research.elamur.ai/free/en/authors/matthew-peters/) · **Year:** 2021 · **Venue:** [Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021](https://md.research.elamur.ai/free/en/venues/findings/) ([Findings of the Association for Computational Linguistics 2021](https://md.research.elamur.ai/free/en/venues/findings/2021/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2021.findings-acl.336/) · [PDF](https://aclanthology.org/2021.findings-acl.336.pdf) · [DOI 10.18653/v1/2021.findings-acl.336](https://doi.org/10.18653/v1/2021.findings-acl.336) · [OpenAlex](https://openalex.org/W3116103312)

**Citations:** 86 citations (OpenAlex, 2026-10-14) · [68](https://md.research.elamur.ai/free/en/papers/ross-2021-explaining-nlp-models-minimal-contrastive/cited-by/) in our library, of the 141,840 papers whose bibliographies we read

## Summary
Popular explanation techniques for NLP classifiers, such as gradient- or attention-based highlights, show which input parts support a prediction. They do not show what would need to change for the model to choose a specific alternative answer. Human explanations, by contrast, usually compare against such an alternative. The authors propose MiCE, which explains a prediction by rewriting the input just enough that a fixed PREDICTOR switches to a chosen contrast label. MiCE has two stages:

1. **Stage 1:** A T5 EDITOR is fine-tuned to fill in masked spans conditioned on a target label. The masked spans are the tokens with the highest gradient attribution.
2. **Stage 2:** The EDITOR edits the input. Binary search sets how much text to mask, and beam search keeps the candidates the PREDICTOR scores highest for the contrast label.

On IMDB, Newsgroups and RACE, the resulting edits change the prediction while staying small and fluent. On IMDB they are comparable to human-written edits. The work makes contrastive explanation practical for spotting model errors and dataset artifacts.

## Key points
- Evaluated on three English tasks: binary sentiment (IMDB), topic classification (Newsgroups) and multiple-choice QA (RACE). Edits are assessed on whether they flip the prediction, how small they are and how fluent they are. The excerpt provided omits the paper's numeric results, so none are given here.
- Two ablations support the design. Gradient-based masking (ℓ1 norm of embedding gradients) outperforms random masking, and adding target labels during EDITOR fine-tuning yields better edits than training without them.
- Stage 1 can use either gold labels (for developers with training data) or the PREDICTOR's own predictions (for users without labeled data).
- The authors demonstrate two use cases: diagnosing individual wrong predictions and exposing dataset artifacts learned by a strong PREDICTOR.
- Code and trained EDITOR models are released at github.com/allenai/mice. The main stated limitation is high computational cost, and noted misuse risks include generating adversarial inputs and careless data augmentation.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [University of Washington](https://md.research.elamur.ai/free/en/universities/university-of-washington/) — University, Seattle, United States · 263 works · 180,581 citations
- [Allen Institute for Artificial Intelligence](https://md.research.elamur.ai/free/en/labs/allen-institute-for-artificial-intelligence/) — Research institute, Seattle, United States · 219 works · 89,712 citations

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 9,086 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 8,889 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 9,296 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 9,206 works

## Cite

Cite as: Alexis Ross, Ana Marasović and Matthew Peters. 2021. Explaining NLP Models via Minimal Contrastive Editing (MiCE). Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{ross2021explaining,
  title = {{Explaining NLP Models via Minimal Contrastive Editing (MiCE)}},
  author = {Alexis Ross, Ana Marasović and Matthew Peters},
  booktitle = {Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021},
  year = {2021},
  doi = {10.18653/v1/2021.findings-acl.336},
  url = {https://doi.org/10.18653/v1/2021.findings-acl.336}
}
```

- [← previous SemEval-2021 Task 1: Lexical Complexity Prediction](https://md.research.elamur.ai/free/en/papers/shardlow-2021-semeval-2021-task-1-lexical/)
- [next → Trafilatura: A Web Scraping Library and Command-Line Tool for Text Discovery and Extraction](https://md.research.elamur.ai/free/en/papers/barbaresi-2021-trafilatura-web-scraping-library-command/)
- [↑ back to papers of 2021](https://md.research.elamur.ai/free/en/papers/2021/page/3/)

## References

75 references, 32 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. David Alvarez-Melis, Hal Daumé III, Jennifer Wortman Vaughan, and Hanna Wallach. 2019. Weight of evidence as a basis for human-oriented explanations. In Workshop on Human-Centric Machine Learning at the 33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, Canada. [find](https://scholar.google.com/scholar?q=David+Alvarez%2DMelis%2C+Hal+Daum%C3%A9+III%2C+Jennifer+Wortman+Vaughan%2C+and+Hanna+Wallach%2E+2019%2E+Weight+of+evidence+as+a+basis+for+human%2Doriented+explanations%2E+In+Workshop+on+Human%2DCentric+Machine+Learning+at+t)
2. Moustafa Alzantot, Yash Sharma, Ahmed Elgohary, Bo-Jhang Ho, Mani Srivastava, and Kai-Wei Chang. 2018. [Generating natural language adversarial examples](https://md.research.elamur.ai/free/en/papers/alzantot-2018-generating-natural-language-adversarial-examples/). In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 2890–2896, Brussels, Belgium. Association for Comp…
3. Jasmijn Bastings, Wilker Aziz, and Ivan Titov. 2019. [Interpretable neural predictions with differentiable binary variables](https://md.research.elamur.ai/free/en/papers/bastings-2019-interpretable-neural-predictions-differentiable-binary/). In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 2963–2977, Florence, Italy. Association for Computational Linguistics.
4. Yonatan Belinkov and James Glass. 2019. [Analysis Methods in Neural Language Processing: A Survey](https://md.research.elamur.ai/free/en/papers/belinkov-2019-analysis-methods-neural-language-processing/). Transactions of the Association for Computational Linguistics, 7:49–72.
5. Oana-Maria Camburu, Tim Rocktäschel, Thomas Lukasiewicz, and Phil Blunsom. 2018. [e-snli: Natural language inference with natural language explanations](https://md.research.elamur.ai/free/en/papers/camburu-2018-e-snli-natural-language-inference/). In Advances in Neural Information Processing Systems, volume 31, pages 9539–9549. Curran Associates, Inc.
6. Shiyu Chang, Yang Zhang, Mo Yu, and Tommi Jaakkola. 2019. A game theoretic approach to class-wise selective rationalization. In Advances in Neural Information Processing Systems, volume 32, pages 10055–10065. Curran Associates, Inc. [find](https://scholar.google.com/scholar?q=Shiyu+Chang%2C+Yang+Zhang%2C+Mo+Yu%2C+and+Tommi+Jaakkola%2E+2019%2E+A+game+theoretic+approach+to+class%2Dwise+selective+rationalization%2E+In+Advances+in+Neural+Information+Processing+Systems%2C+volume+32%2C+pages+1005)
7. Seth Chin-Parker and Julie A Cantelon. 2017. Contrastive constraints guide explanation-based category learning. Cognitive Science, 41 6:1645–1655. [find](https://scholar.google.com/scholar?q=Seth+Chin%2DParker+and+Julie+A+Cantelon%2E+2017%2E+Contrastive+constraints+guide+explanation%2Dbased+category+learning%2E+Cognitive+Science%2C+41+6%3A1645%E2%80%931655%2E)
8. Susanne Dandl, Christoph Molnar, Martin Binder, and Bernd Bischl. 2020. Multi-objective counterfactual explanations. In Parallel Problem Solving from Nature – PPSN XVI, pages 448–469, Cham. Springer International Publishing. [find](https://scholar.google.com/scholar?q=Susanne+Dandl%2C+Christoph+Molnar%2C+Martin+Binder%2C+and+Bernd+Bischl%2E+2020%2E+Multi%2Dobjective+counterfactual+explanations%2E+In+Parallel+Problem+Solving+from+Nature+%E2%80%93+PPSN+XVI%2C+pages+448%E2%80%93469%2C+Cham%2E+Springer+I)
9. Jay DeYoung, Sarthak Jain, Nazneen Fatema Rajani, Eric Lehman, Caiming Xiong, Richard Socher, and Byron C. Wallace. 2020. [ERASER: A benchmark to evaluate rationalized NLP models](https://md.research.elamur.ai/free/en/papers/deyoung-2020-eraser-benchmark-evaluate-rationalized-nlp/). In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 4443–4458. Association…
10. Javid Ebrahimi, Anyi Rao, Daniel Lowd, and Dejing Dou. 2018. [HotFlip: White-box adversarial examples for text classification](https://md.research.elamur.ai/free/en/papers/ebrahimi-2018-hotflip-white-box-adversarial-examples/). In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 31–36, Melbourne, Australia. Association for Comput…
11. Angela Fan, Mike Lewis, and Yann Dauphin. 2018. Hierarchical neural story generation. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 889–898, Melbourne, Australia. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Angela+Fan%2C+Mike+Lewis%2C+and+Yann+Dauphin%2E+2018%2E+Hierarchical+neural+story+generation%2E+In+Proceedings+of+the+56th+Annual+Meeting+of+the+Association+for+Computational+Linguistics+%28Volume+1%3A+Long+Papers%29)
12. Amir Feder, Nadav Oved, Uri Shalit, and Roi Reichart. 2021. [CausaLM: Causal Model Explanation Through Counterfactual Language Models](https://md.research.elamur.ai/free/en/papers/feder-2021-causalm-causal-model-explanation-through/). Computational Linguistics, pages 1–54.
13. Zhenxin Fu, Xiaoye Tan, Nanyun Peng, Dongyan Zhao, and Rui Yan. 2018. [Style transfer in text: Exploration and evaluation](https://md.research.elamur.ai/free/en/papers/fu-2017-style-transfer-text-exploration-evaluation/). In AAAI Conference on Artificial Intelligence.
14. [Matt Gardner, Yoav Artzi, Victoria Basmov, Jonathan Berant, Ben Bogin, Sihao Chen, Pradeep Dasigi, Dheeru Dua, Yanai Elazar, Ananth Gottumukkala, Nitish Gupta, Hannaneh Hajishirzi, Gabriel Ilharco, Daniel Khashabi, Kevin Lin, Jiangming Liu, Nelson F. Liu, Phoebe Mulcaire, Qiang Ning, Sameer Singh, N…](https://md.research.elamur.ai/free/en/papers/gardner-2020-evaluating-models-local-decision-boundaries/)
15. Matt Gardner, Joel Grus, Mark Neumann, Oyvind Tafjord, Pradeep Dasigi, Nelson F. Liu, Matthew Peters, Michael Schmitz, and Luke S. Zettlemoyer. 2017. [Allennlp: A deep semantic natural language processing platform](https://md.research.elamur.ai/free/en/papers/gardner-2018-allennlp-deep-semantic-natural-language/).
16. Siddhant Garg and Goutham Ramakrishnan. 2020. [BAE: BERT-based adversarial examples for text classification](https://md.research.elamur.ai/free/en/papers/garg-2020-bae-bert-based-adversarial-examples/). In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 6174–6181. Association for Computational Linguistics.
17. Navita Goyal, Balaji Vasan Srinivasan, N. Anandhavelu, and Abhilasha Sancheti. 2020. Multidimensional style transfer for partially annotated data using language models as discriminators. ArXiv, arXiv:2010.11578. — [arXiv:2010.11578](https://arxiv.org/abs/2010.11578) [find](https://scholar.google.com/scholar?q=Navita+Goyal%2C+Balaji+Vasan+Srinivasan%2C+N%2E+Anandhavelu%2C+and+Abhilasha+Sancheti%2E+2020%2E+Multidimensional+style+transfer+for+partially+annotated+data+using+language+models+as+discriminators%2E+ArXiv%2C+arXiv%3A)
18. Yash Goyal, Ziyan Wu, Jan Ernst, Dhruv Batra, Devi Parikh, and Stefan Lee. 2019. Counterfactual visual explanations. In Proceedings of the 36th International Conference on Machine Learning, volume 97 of Proceedings of Machine Learning Research, pages 2376–2384, Long Beach, California, USA. PMLR. [find](https://scholar.google.com/scholar?q=Yash+Goyal%2C+Ziyan+Wu%2C+Jan+Ernst%2C+Dhruv+Batra%2C+Devi+Parikh%2C+and+Stefan+Lee%2E+2019%2E+Counterfactual+visual+explanations%2E+In+Proceedings+of+the+36th+International+Conference+on+Machine+Learning%2C+volume+97+)
19. Lisa Anne Hendricks, Ronghang Hu, Trevor Darrell, and Zeynep Akata. 2018. Grounding visual explanations. In Computer Vision – ECCV 2018, pages 269–286, Cham. Springer International Publishing. [find](https://scholar.google.com/scholar?q=Lisa+Anne+Hendricks%2C+Ronghang+Hu%2C+Trevor+Darrell%2C+and+Zeynep+Akata%2E+2018%2E+Grounding+visual+explanations%2E+In+Computer+Vision+%E2%80%93+ECCV+2018%2C+pages+269%E2%80%93286%2C+Cham%2E+Springer+International+Publishing%2E)
20. Denis Hilton. 2017. Social Attribution and Explanation. Oxford University Press. [find](https://scholar.google.com/scholar?q=Denis+Hilton%2E+2017%2E+Social+Attribution+and+Explanation%2E+Oxford+University+Press%2E)
21. Ari Holtzman, Jan Buys, Li Du, Maxwell Forbes, and Yejin Choi. 2020. The curious case of neural text degeneration. In International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Ari+Holtzman%2C+Jan+Buys%2C+Li+Du%2C+Maxwell+Forbes%2C+and+Yejin+Choi%2E+2020%2E+The+curious+case+of+neural+text+degeneration%2E+In+International+Conference+on+Learning+Representations%2E)
22. Mohit Iyyer, John Wieting, Kevin Gimpel, and Luke Zettlemoyer. 2018. [Adversarial example generation with syntactically controlled paraphrase networks](https://md.research.elamur.ai/free/en/papers/iyyer-2018-adversarial-example-generation-syntactically-controlled/). In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Vo…
23. Alon Jacovi and Y. Goldberg. 2020. [Aligning faithful interpretations with their social attribution](https://md.research.elamur.ai/free/en/papers/jacovi-2021-aligning-faithful-interpretations-their-social/). ArXiv, arXiv:2006.01067.
24. Alon Jacovi, Swabha Swayamdipta, Shauli Ravfogel, Yanai Elazar, Yejin Choi, and Yoav Goldberg. 2021. Contrastive explanations for model interpretability. ArXiv:2103.01378. [find](https://scholar.google.com/scholar?q=Alon+Jacovi%2C+Swabha+Swayamdipta%2C+Shauli+Ravfogel%2C+Yanai+Elazar%2C+Yejin+Choi%2C+and+Yoav+Goldberg%2E+2021%2E+Contrastive+explanations+for+model+interpretability%2E+ArXiv%3A2103%2E01378%2E)
25. Sarthak Jain, Sarah Wiegreffe, Yuval Pinter, and Byron C. Wallace. 2020. [Learning to faithfully rationalize by construction](https://md.research.elamur.ai/free/en/papers/jain-2020-learning-faithfully-rationalize-construction/). In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 4459–4473. Association for Computational Linguistics.
26. Robin Jia and Percy Liang. 2017. [Adversarial examples for evaluating reading comprehension systems](https://md.research.elamur.ai/free/en/papers/jia-2017-adversarial-examples-evaluating-reading-comprehension/). In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 2021–2031, Copenhagen, Denmark. Association for Computational Linguistics.
27. Amir-Hossein Karimi, G. Barthe, B. Balle, and I. Valera. 2020. Model-agnostic counterfactual explanations for consequential decisions. Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics (AISTATS). [find](https://scholar.google.com/scholar?q=Amir%2DHossein+Karimi%2C+G%2E+Barthe%2C+B%2E+Balle%2C+and+I%2E+Valera%2E+2020%2E+Model%2Dagnostic+counterfactual+explanations+for+consequential+decisions%2E+Proceedings+of+the+23rd+International+Conference+on+Artificial+In)
28. Divyansh Kaushik, Eduard Hovy, and Zachary Lipton. 2020. Learning the difference that makes a difference with counterfactually-augmented data. In International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Divyansh+Kaushik%2C+Eduard+Hovy%2C+and+Zachary+Lipton%2E+2020%2E+Learning+the+difference+that+makes+a+difference+with+counterfactually%2Daugmented+data%2E+In+International+Conference+on+Learning+Representations%2E)
29. Guokun Lai, Qizhe Xie, Hanxiao Liu, Yiming Yang, and Eduard Hovy. 2017. [RACE: Large-scale ReAding comprehension dataset from examinations](https://md.research.elamur.ai/free/en/papers/lai-2017-race-large-scale-reading-comprehension/). In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 785–794, Copenhagen, Denmark. Association for Computational Ling…
30. Ken Lang. 1995. Newsweeder: Learning to filter netnews. In Proceedings of the Twelfth International Conference on Machine Learning, pages 331–339. [find](https://scholar.google.com/scholar?q=Ken+Lang%2E+1995%2E+Newsweeder%3A+Learning+to+filter+netnews%2E+In+Proceedings+of+the+Twelfth+International+Conference+on+Machine+Learning%2C+pages+331%E2%80%93339%2E)
31. Tao Lei, Regina Barzilay, and Tommi Jaakkola. 2016. [Rationalizing neural predictions](https://md.research.elamur.ai/free/en/papers/lei-2016-rationalizing-neural-predictions/). In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 107–117, Austin, Texas. Association for Computational Linguistics.
32. Chuanrong Li, Lin Shengshuo, Zeyu Liu, Xinyi Wu, Xuhui Zhou, and Shane Steinert-Threlkeld. 2020a. Linguistically-informed transformations (LIT): A method for automatically generating contrast sets. In Proceedings of the Third BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP… [find](https://scholar.google.com/scholar?q=Chuanrong+Li%2C+Lin+Shengshuo%2C+Zeyu+Liu%2C+Xinyi+Wu%2C+Xuhui+Zhou%2C+and+Shane+Steinert%2DThrelkeld%2E+2020a%2E+Linguistically%2Dinformed+transformations+%28LIT%29%3A+A+method+for+automatically+generating+contrast+sets%2E+In)
33. Juncen Li, Robin Jia, He He, and Percy Liang. 2018. [Delete, retrieve, generate: a simple approach to sentiment and style transfer](https://md.research.elamur.ai/free/en/papers/li-2018-delete-retrieve-generate-simple-approach/). In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)…
34. Linyang Li, Ruotian Ma, Qipeng Guo, Xiangyang Xue, and Xipeng Qiu. 2020b. [BERT-ATTACK: Adversarial attack against BERT using BERT](https://md.research.elamur.ai/free/en/papers/li-2020-bert-attack-adversarial-attack-against/). In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 6193–6202. Association for Computational Linguistics.
35. Weixin Liang, James Zou, and Zhou Yu. 2020. ALICE: Active learning with contrastive natural language explanations. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 4380–4391, Online. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Weixin+Liang%2C+James+Zou%2C+and+Zhou+Yu%2E+2020%2E+ALICE%3A+Active+learning+with+contrastive+natural+language+explanations%2E+In+Proceedings+of+the+2020+Conference+on+Empirical+Methods+in+Natural+Language+Proces)
36. Peter Lipton. 1990. Contrastive explanation. Royal Institute of Philosophy Supplement, 27:247–266. [find](https://scholar.google.com/scholar?q=Peter+Lipton%2E+1990%2E+Contrastive+explanation%2E+Royal+Institute+of+Philosophy+Supplement%2C+27%3A247%E2%80%93266%2E)
37. Y. Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, M. Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. RoBERTa: A robustly optimized BERT pretraining approach. ArXiv, arXiv:1907.11692. [find](https://scholar.google.com/scholar?q=Y%2E+Liu%2C+Myle+Ott%2C+Naman+Goyal%2C+Jingfei+Du%2C+Mandar+Joshi%2C+Danqi+Chen%2C+Omer+Levy%2C+M%2E+Lewis%2C+Luke+Zettlemoyer%2C+and+Veselin+Stoyanov%2E+2019%2E+RoBERTa%3A+A+robustly+optimized+BERT+pretraining+approach%2E+ArXiv%2C+)
38. Arnaud Van Looveren and Janis Klaise. 2019. Interpretable counterfactual explanations guided by prototypes. ArXiv, arXiv:1907.02584. — [arXiv:1907.02584](https://arxiv.org/abs/1907.02584) [find](https://scholar.google.com/scholar?q=Arnaud+Van+Looveren+and+Janis+Klaise%2E+2019%2E+Interpretable+counterfactual+explanations+guided+by+prototypes%2E+ArXiv%2C+arXiv%3A1907%2E02584%2E+%E2%80%94+%5BarXiv%3A1907%2E02584%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F1907%2E02584%29)
39. Andrew L. Maas, Raymond E. Daly, Peter T. Pham, Dan Huang, Andrew Y. Ng, and Christopher Potts. 2011. [Learning word vectors for sentiment analysis](https://md.research.elamur.ai/free/en/papers/maas-2011-learning-word-vectors-sentiment-analysis/). In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, pages 142–150, Portland, Oregon…
40. Nishtha Madaan, Inkit Padhi, Naveen Panwar, and Diptikalyan Saha. 2021. Generate your counterfactuals: Towards controlled counterfactual generation for text. In Proceedings of the AAAI Conference on Artificial Intelligence. [find](https://scholar.google.com/scholar?q=Nishtha+Madaan%2C+Inkit+Padhi%2C+Naveen+Panwar%2C+and+Diptikalyan+Saha%2E+2021%2E+Generate+your+counterfactuals%3A+Towards+controlled+counterfactual+generation+for+text%2E+In+Proceedings+of+the+AAAI+Conference+on+A)
41. Eric Malmi, Aliaksei Severyn, and Sascha Rothe. 2020. Unsupervised text style transfer with padded masked language models. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 8671–8680. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Eric+Malmi%2C+Aliaksei+Severyn%2C+and+Sascha+Rothe%2E+2020%2E+Unsupervised+text+style+transfer+with+padded+masked+language+models%2E+In+Proceedings+of+the+2020+Conference+on+Empirical+Methods+in+Natural+Languag)
42. Chris Russell. 2019. Efficient search for diverse coherent explanations. In Proceedings of the Conference on Fairness, Accountability, and Transparency. [find](https://scholar.google.com/scholar?q=Chris+Russell%2E+2019%2E+Efficient+search+for+diverse+coherent+explanations%2E+In+Proceedings+of+the+Conference+on+Fairness%2C+Accountability%2C+and+Transparency%2E)
43. Tim Miller. 2019. [Explanation in Artificial Intelligence: Insights from the social sciences](https://md.research.elamur.ai/free/en/papers/miller-2017-explanation-artificial-intelligence-insights-social/). Artificial Intelligence, 267:1–38.
44. Julian Salazar, Davis Liang, Toan Q. Nguyen, and Katrin Kirchhoff. 2020. [Masked language model scoring](https://md.research.elamur.ai/free/en/papers/salazar-2020-masked-language-model-scoring/). In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 2699–2712. Association for Computational Linguistics.
45. Sharan Narang, Colin Raffel, Katherine Lee, Adam Roberts, Noah Fiedel, and Karishma Malkan. 2020. WT5?! training text-to-text models to explain their predictions. arXiv:2004.14546. [find](https://scholar.google.com/scholar?q=Sharan+Narang%2C+Colin+Raffel%2C+Katherine+Lee%2C+Adam+Roberts%2C+Noah+Fiedel%2C+and+Karishma+Malkan%2E+2020%2E+WT5%3F%21+training+text%2Dto%2Dtext+models+to+explain+their+predictions%2E+arXiv%3A2004%2E14546%2E)
46. Lei Sha, Patrick Hohenecker, and Thomas Lukasiewicz. 2021. Controlling text edition by changing answers of specific questions. ArXiv:2105.11018. [find](https://scholar.google.com/scholar?q=Lei+Sha%2C+Patrick+Hohenecker%2C+and+Thomas+Lukasiewicz%2E+2021%2E+Controlling+text+edition+by+changing+answers+of+specific+questions%2E+ArXiv%3A2105%2E11018%2E)
47. B. Pal and S. Tople. 2020. To transfer or not to transfer: Misclassification attacks against transfer learned text classifiers. ArXiv, arXiv:2001.02438. — [arXiv:2001.02438](https://arxiv.org/abs/2001.02438) [find](https://scholar.google.com/scholar?q=B%2E+Pal+and+S%2E+Tople%2E+2020%2E+To+transfer+or+not+to+transfer%3A+Misclassification+attacks+against+transfer+learned+text+classifiers%2E+ArXiv%2C+arXiv%3A2001%2E02438%2E+%E2%80%94+%5BarXiv%3A2001%2E02438%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2001)
48. Judea Pearl. 2009. Causality: Models, Reasoning and Inference, 2nd edition. Cambridge University Press, USA. [find](https://scholar.google.com/scholar?q=Judea+Pearl%2E+2009%2E+Causality%3A+Models%2C+Reasoning+and+Inference%2C+2nd+edition%2E+Cambridge+University+Press%2C+USA%2E)
49. Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. 2020. [Exploring the limits of transfer learning with a unified text-to-text transformer](https://md.research.elamur.ai/free/en/papers/raffel-2019-exploring-limits-transfer-learning-unified/). Journal of Machine Learning Research, 21(140):1–67.
50. Nazneen Fatema Rajani, Bryan McCann, Caiming Xiong, and Richard Socher. 2019. [Explain yourself! leveraging language models for commonsense reasoning](https://md.research.elamur.ai/free/en/papers/rajani-2019-explain-yourself-leveraging-language-models/). In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 4932–4942, Florence, Italy. Association for Computat…
51. D Raj Reddy. 1977. Speech understanding systems: A summary of results of the five-year research effort. [find](https://scholar.google.com/scholar?q=D+Raj+Reddy%2E+1977%2E+Speech+understanding+systems%3A+A+summary+of+results+of+the+five%2Dyear+research+effort%2E)
52. Shuhuai Ren, Yihe Deng, Kun He, and Wanxiang Che. 2019. [Generating natural language adversarial examples through probability weighted word saliency](https://md.research.elamur.ai/free/en/papers/ren-2019-generating-natural-language-adversarial-examples/). In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 1085–1097, Florence, Italy. Association for Computati…
53. Marco Tulio Ribeiro, Sameer Singh, and Carlos Guestrin. 2016. ["why should i trust you?": Explaining the predictions of any classifier](https://md.research.elamur.ai/free/en/papers/ribeiro-2016-why-should-i-trust-explaining/). Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.
54. Marco Tulio Ribeiro, Sameer Singh, and Carlos Guestrin. 2018. Semantically equivalent adversarial rules for debugging NLP models. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 856–865, Melbourne, Australia. Association for C… [find](https://scholar.google.com/scholar?q=Marco+Tulio+Ribeiro%2C+Sameer+Singh%2C+and+Carlos+Guestrin%2E+2018%2E+Semantically+equivalent+adversarial+rules+for+debugging+NLP+models%2E+In+Proceedings+of+the+56th+Annual+Meeting+of+the+Association+for+Compu)
55. Mireia Ribera and Àgata Lapedriza. 2019. Can We Do Better Explanations? A Proposal of User-Centered Explainable AI. In ACM IUI Workshop. [find](https://scholar.google.com/scholar?q=Mireia+Ribera+and+%C3%80gata+Lapedriza%2E+2019%2E+Can+We+Do+Better+Explanations%3F+A+Proposal+of+User%2DCentered+Explainable+AI%2E+In+ACM+IUI+Workshop%2E)
56. Karen Simonyan, Andrea Vedaldi, and Andrew Zisserman. 2014. [Deep inside convolutional networks: Visualising image classification models and saliency maps](https://md.research.elamur.ai/free/en/papers/simonyan-2013-deep-inside-convolutional-networks-visualising/). In 2nd International Conference on Learning Representations, ICLR 2014, Banff, AB, Canada, April 14-16, 2014, Workshop Track Proceedings.
57. Jacob Sippy, Gagan Bansal, and Daniel S. Weld. 2020. Data staining: A method for comparing faithfulness of explainers. In 2020 ICML Workshop on Human Interpretability in Machine Learning (WHI 2020). [find](https://scholar.google.com/scholar?q=Jacob+Sippy%2C+Gagan+Bansal%2C+and+Daniel+S%2E+Weld%2E+2020%2E+Data+staining%3A+A+method+for+comparing+faithfulness+of+explainers%2E+In+2020+ICML+Workshop+on+Human+Interpretability+in+Machine+Learning+%28WHI+2020%29%2E)
58. D. Smilkov, Nikhil Thorat, Been Kim, F. Viégas, and M. Wattenberg. 2017. Smoothgrad: removing noise by adding noise. In ICML Workshop on Visualization for Deep Learning. [find](https://scholar.google.com/scholar?q=D%2E+Smilkov%2C+Nikhil+Thorat%2C+Been+Kim%2C+F%2E+Vi%C3%A9gas%2C+and+M%2E+Wattenberg%2E+2017%2E+Smoothgrad%3A+removing+noise+by+adding+noise%2E+In+ICML+Workshop+on+Visualization+for+Deep+Learning%2E)
59. Congzheng Song, Alexander Rush, and Vitaly Shmatikov. 2020. Adversarial semantic collisions. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 4198–4210, Online. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Congzheng+Song%2C+Alexander+Rush%2C+and+Vitaly+Shmatikov%2E+2020%2E+Adversarial+semantic+collisions%2E+In+Proceedings+of+the+2020+Conference+on+Empirical+Methods+in+Natural+Language+Processing+%28EMNLP%29%2C+pages+41)
60. Kaiser Sun and Ana Marasović. 2021. Effective attention sheds light on interpretability. In Findings of ACL. [find](https://scholar.google.com/scholar?q=Kaiser+Sun+and+Ana+Marasovic%CC%81%2E+2021%2E+Effective+attention+sheds+light+on+interpretability%2E+In+Findings+of+ACL%2E)
61. Mukund Sundararajan, Ankur Taly, and Qiqi Yan. 2017. Axiomatic attribution for deep networks. In Proceedings of the 34th International Conference on Machine Learning - Volume 70, page 3319–3328. JMLR.org. [find](https://scholar.google.com/scholar?q=Mukund+Sundararajan%2C+Ankur+Taly%2C+and+Qiqi+Yan%2E+2017%2E+Axiomatic+attribution+for+deep+networks%2E+In+Proceedings+of+the+34th+International+Conference+on+Machine+Learning+%2D+Volume+70%2C+page+3319%E2%80%933328%2E+JMLR%2E)
62. Alon Talmor, Jonathan Herzig, Nicholas Lourie, and Jonathan Berant. 2019. [CommonsenseQA: A question answering challenge targeting commonsense knowledge](https://md.research.elamur.ai/free/en/papers/talmor-2019-commonsenseqa-question-answering-challenge-targeting/). In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies,…
63. Damien Teney, Ehsan Abbasnejad, and A. V. D. Hengel. 2020. Learning what makes a difference from counterfactual examples and gradient supervision. In Proceedings of the European Conference on Computer Vision (ECCV). [find](https://scholar.google.com/scholar?q=Damien+Teney%2C+Ehsan+Abbasnejad%2C+and+A%2E+V%2E+D%2E+Hengel%2E+2020%2E+Learning+what+makes+a+difference+from+counterfactual+examples+and+gradient+supervision%2E+In+Proceedings+of+the+European+Conference+on+Computer)
64. Bas C Van Fraassen. 1980. The scientific image. Oxford University Press. [find](https://scholar.google.com/scholar?q=Bas+C+Van+Fraassen%2E+1980%2E+The+scientific+image%2E+Oxford+University+Press%2E)
65. Jesse Vig, Sebastian Gehrmann, Yonatan Belinkov, Sharon Qian, Daniel Nevo, Yaron Singer, and Stuart Shieber. 2020. Investigating gender bias in language models using causal mediation analysis. In Advances in Neural Information Processing Systems, volume 33, pages 12388–12401. Curran Associates, Inc. [find](https://scholar.google.com/scholar?q=Jesse+Vig%2C+Sebastian+Gehrmann%2C+Yonatan+Belinkov%2C+Sharon+Qian%2C+Daniel+Nevo%2C+Yaron+Singer%2C+and+Stuart+Shieber%2E+2020%2E+Investigating+gender+bias+in+language+models+using+causal+mediation+analysis%2E+In+Adva)
66. S. Wachter, Brent D. Mittelstadt, and Chris Russell. 2017. Counterfactual explanations without opening the black box: Automated decisions and the gdpr. European Economics: Microeconomics & Industrial Organization eJournal. [find](https://scholar.google.com/scholar?q=S%2E+Wachter%2C+Brent+D%2E+Mittelstadt%2C+and+Chris+Russell%2E+2017%2E+Counterfactual+explanations+without+opening+the+black+box%3A+Automated+decisions+and+the+gdpr%2E+European+Economics%3A+Microeconomics+%26+Industrial+)
67. Sarah Wiegreffe and Yuval Pinter. 2019. [Attention is not not explanation](https://md.research.elamur.ai/free/en/papers/wiegreffe-2019-attention-is-not-not-explanation/). In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 11–20, Hong Kong, China. Association for…
68. Omar Zaidan, Jason Eisner, and Christine Piatko. 2007. [Using “annotator rationales” to improve machine learning for text categorization](https://md.research.elamur.ai/free/en/papers/zaidan-2007-annotator-rationales-improve-machine-learning/). In Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics; Proceedings of the Main Confere…
69. Rowan Zellers, Yonatan Bisk, Ali Farhadi, and Yejin Choi. 2019. From Recognition to Cognition: Visual Commonsense Reasoning. In CVPR. [find](https://scholar.google.com/scholar?q=Rowan+Zellers%2C+Yonatan+Bisk%2C+Ali+Farhadi%2C+and+Yejin+Choi%2E+2019%2E+From+Recognition+to+Cognition%3A+Visual+Commonsense+Reasoning%2E+In+CVPR%2E)
70. Huangzhao Zhang, Hao Zhou, Ning Miao, and Lei Li. 2019. Generating fluent adversarial examples for natural languages. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 5564–5569, Florence, Italy. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Huangzhao+Zhang%2C+Hao+Zhou%2C+Ning+Miao%2C+and+Lei+Li%2E+2019%2E+Generating+fluent+adversarial+examples+for+natural+languages%2E+In+Proceedings+of+the+57th+Annual+Meeting+of+the+Association+for+Computational+Lin)
71. [Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Clement Delangue, Anthony Moi, Pier-ric Cistac, Tim Rault, Rémi Louf, Morgan Funtowicz, Joe Davison, Sam Shleifer, Patrick von Platen, Clara Ma, Yacine Jernite, Julien Plu, Canwen Xu, Teven Le Scao, Sylvain Gugger, Mariama Drame, Quentin Lho…](https://md.research.elamur.ai/free/en/papers/wolf-2020-transformers-state-art-natural-language/)
72. Tongshuang Wu, Marco Túlio Ribeiro, J. Heer, and Daniel S. Weld. 2021. Polyjuice: Automated, general-purpose counterfactual generation. arXiv:2101.00288. — [arXiv:2101.00288](https://arxiv.org/abs/2101.00288) [find](https://scholar.google.com/scholar?q=Tongshuang+Wu%2C+Marco+T%C3%BAlio+Ribeiro%2C+J%2E+Heer%2C+and+Daniel+S%2E+Weld%2E+2021%2E+Polyjuice%3A+Automated%2C+general%2Dpurpose+counterfactual+generation%2E+arXiv%3A2101%2E00288%2E+%E2%80%94+%5BarXiv%3A2101%2E00288%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F210)
73. Xing Wu, Tao Zhang, Liangjun Zang, Jizhong Han, and Songlin Hu. 2019. Mask and infill: Applying masked language model for sentiment transfer. In Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, IJCAI-19, pages 5271–5277. International Joint Conferences on A… [find](https://scholar.google.com/scholar?q=Xing+Wu%2C+Tao+Zhang%2C+Liangjun+Zang%2C+Jizhong+Han%2C+and+Songlin+Hu%2E+2019%2E+Mask+and+infill%3A+Applying+masked+language+model+for+sentiment+transfer%2E+In+Proceedings+of+the+Twenty%2DEighth+International+Joint+Co)
74. Linyi Yang, Eoin Kenny, Tin Lok James Ng, Yi Yang, Barry Smyth, and Ruihai Dong. 2020. Generating plausible counterfactual explanations for deep transformers in financial text classification. In Proceedings of the 28th International Conference on Computational Linguistics, pages 6150–6160, Barcelona… [find](https://scholar.google.com/scholar?q=Linyi+Yang%2C+Eoin+Kenny%2C+Tin+Lok+James+Ng%2C+Yi+Yang%2C+Barry+Smyth%2C+and+Ruihai+Dong%2E+2020%2E+Generating+plausible+counterfactual+explanations+for+deep+transformers+in+financial+text+classification%2E+In+Proce)
75. Mo Yu, Shiyu Chang, Yang Zhang, and Tommi Jaakkola. 2019. [Rethinking cooperative rationalization: Introspective extraction and complement control](https://md.research.elamur.ai/free/en/papers/yu-2019-rethinking-cooperative-rationalization-introspective-extraction/). In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing

*Updated 24 October 2026*