---
title: "Naturalistic Causal Probing for Morpho-Syntax — Amini 2023"
description: "The authors propose causal probing through input-level interventions on real… 90% accuracy. 49 references, cited by 14 papers here."
authors: ["Afra Amini", "Tiago Pimentel", "Clara Meister", "Ryan Cotterell"]
year: 2023
venue: "Transactions of the Association for Computational Linguistics"
source: "https://aclanthology.org/2023.tacl-1.23/"
doi: "10.1162/tacl_a_00554"
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/amini-2023-naturalistic-causal-probing-morpho-syntax/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/amini-2023-naturalistic-causal-probing-morpho-syntax/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2023](https://md.research.elamur.ai/free/en/papers/2023/page/12/) / Naturalistic Causal Probing for Morpho-Syntax

# Naturalistic Causal Probing for Morpho-Syntax

**Authors:** [Afra Amini](https://md.research.elamur.ai/free/en/authors/afra-amini/), [Tiago Pimentel](https://md.research.elamur.ai/free/en/authors/tiago-pimentel/), [Clara Meister](https://md.research.elamur.ai/free/en/authors/clara-meister/) and [Ryan Cotterell](https://md.research.elamur.ai/free/en/authors/ryan-cotterell/) · **Year:** 2023 · **Venue:** [Transactions of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/tacl/) ([Transactions of the Association for Computational Linguistics (TACL) 2023](https://md.research.elamur.ai/free/en/venues/tacl/2023/)) · **Publisher:** [The MIT Press](https://md.research.elamur.ai/free/en/publishers/the-mit-press/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2023.tacl-1.23/) · [PDF](https://aclanthology.org/2023.tacl-1.23.pdf) · [DOI 10.1162/tacl\_a\_00554](https://doi.org/10.1162/tacl_a_00554) · [OpenAlex](https://openalex.org/W4382623032)

**Citations:** 5 citations (OpenAlex, 2026-10-14) · [14](https://md.research.elamur.ai/free/en/papers/amini-2023-naturalistic-causal-probing-morpho-syntax/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Conventional (correlational) probes can show that a property is decodable from a model's representations. They cannot show whether the property actually causes those representations, and correlated linguistic features can inflate their scores. The authors propose causal probing through input-level interventions on real sentences instead of templates. A heuristic algorithm uses each sentence's dependency parse to replace a focus noun with a form differing only in gender or number. It then reinflects the words that must agree with it, such as determiners, adjectival modifiers, verbs and copulas. The resulting sentences are called naturalistic counterfactuals. With them, the authors estimate the average treatment effect (ATE) of grammatical gender and number on noun representations in Spanish or multilingual BERT, RoBERTa and GPT-2. The ATE estimates stay stable across corpora, unlike naïve correlational or template-based estimates. Both features are captured by a few directions in representation space, and RoBERTa shows gender-skewed adjective preferences. Gender probes score above 90% on original data but drop to roughly 60% once counterfactuals are added. This shows that correlational probing can overstate what models encode.

## Key points
- Counterfactuals are built automatically by reinflecting agreement relations in the dependency tree, which avoids the narrow coverage and bias of hand-made templates.
- The models studied are the Spanish versions of BERT, RoBERTa and GPT-2 where they exist, otherwise the multilingual versions. Code is at github.com/rycolab/naturalistic-causal-probing.
- A back-door adjustment proof shows that the ATE can be computed from ordinary conditional expectations without the do-operator.
- The gender-bias test used 30 Spanish adjectives. RoBERTa tends to pair feminine nouns with hermoso/hermosa ("beautiful"), whereas masculine nouns are more often paired with racional ("rational").
- Probes predicting gender from sentence-level representations fall from over 90% accuracy to about 60%, close to chance, on counterfactually augmented data.

*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 Cambridge](https://md.research.elamur.ai/free/en/universities/university-of-cambridge/) — University, Cambridge, United Kingdom · 256 works · 123,373 citations
- [ETH Zurich](https://md.research.elamur.ai/free/en/universities/eth-zurich/) — University, Zurich, Switzerland · 84 works · 9,181 citations

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works

🧭 Topics (2): [📐 Syntax & grammar formalisms](https://md.research.elamur.ai/free/en/topics/syntax-grammar/) · 221 works · [🔬 Interpretability](https://md.research.elamur.ai/free/en/topics/interpretability/) · 149 works

## Cite

Cite as: Afra Amini, Tiago Pimentel, Clara Meister and Ryan Cotterell. 2023. Naturalistic Causal Probing for Morpho-Syntax. Transactions of the Association for Computational Linguistics.

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

```bibtex
@article{amini2023naturalistic,
  title = {{Naturalistic Causal Probing for Morpho-Syntax}},
  author = {Afra Amini, Tiago Pimentel, Clara Meister and Ryan Cotterell},
  journal = {Transactions of the Association for Computational Linguistics},
  year = {2023},
  doi = {10.1162/tacl\_a\_00554},
  url = {https://doi.org/10.1162/tacl_a_00554}
}
```

- [← previous MPSA-DenseNet: A novel deep learning model for English accent classification](https://md.research.elamur.ai/free/en/papers/song-2023-mpsa-densenet-novel-deep-learning/)
- [next → Quality-Diversity through AI Feedback](https://md.research.elamur.ai/free/en/papers/bradley-2023-quality-diversity-through-ai-feedback/)
- [↑ back to papers of 2023](https://md.research.elamur.ai/free/en/papers/2023/page/12/)

## References

49 references, 24 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Yossi Adi, Einat Kermany, Yonatan Belinkov, Ofer Lavi, and Yoav Goldberg. 2017. [Fine-grained analysis of sentence embeddings using auxiliary prediction tasks](https://md.research.elamur.ai/free/en/papers/adi-2016-fine-grained-analysis-sentence-embeddings/). In 5th International Conference on Learning Representations (Conference Track). https://doi.org/10.1147/JRD.2017.2702858 [↗](https://doi.org/10.1147/JRD.2017.2702858)
2. Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D. Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel Ziegler, Jeffrey Wu, Clemens Winter, Chr… — [Language Models are Few-Shot Learners](https://md.research.elamur.ai/free/en/papers/brown-2020-language-models-few-shot-learners/)
3. Guillaume Alain and Yoshua Bengio. 2017. Understanding intermediate layers using linear classifier probes. In 5th International Conference on Learning Representations (Workshop Track). [find](https://scholar.google.com/scholar?q=Guillaume+Alain+and+Yoshua+Bengio%2E+2017%2E+Understanding+intermediate+layers+using+linear+classifier+probes%2E+In+5th+International+Conference+on+Learning+Representations+%28Workshop+Track%29%2E)
4. Marion Bartl, Malvina Nissim, and Albert Gatt. 2020. [Unmasking contextual stereotypes: Measuring and mitigating BERT’s gender bias](https://md.research.elamur.ai/free/en/papers/bartl-2020-unmasking-contextual-stereotypes-measuring-mitigating/). In Proceedings of the Second Workshop on Gender Bias in Natural Language Processing, pages 1–16, Barcelona, Spain (Online). Association for Computational Linguistics.
5. Alexis Conneau, Kartikay Khandelwal, Naman Goyal, Vishrav Chaudhary, Guillaume Wenzek, Francisco Guzmán, Edouard Grave, Myle Ott, Luke Zettlemoyer, and Veselin Stoyanov. 2020. [Unsupervised cross-lingual representation learning at scale](https://md.research.elamur.ai/free/en/papers/conneau-2018-what-you-can-cram-into/). In Proceedings of the 58th Annual Meeting of the Association f…
6. Yonatan Belinkov. 2021. Probing classifiers: Promises, shortcomings, and alternatives. arXiv preprint arXiv:2102.12452. — [arXiv:2102.12452](https://arxiv.org/abs/2102.12452) [find](https://scholar.google.com/scholar?q=Yonatan+Belinkov%2E+2021%2E+Probing+classifiers%3A+Promises%2C+shortcomings%2C+and+alternatives%2E+arXiv+preprint+arXiv%3A2102%2E12452%2E+%E2%80%94+%5BarXiv%3A2102%2E12452%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2102%2E12452%29)
7. Yonatan Belinkov, Lluı́s Màrquez, Hassan Sajjad, Nadir Durrani, Fahim Dalvi, and James Glass. 2017. [Evaluating layers of representation in neural machine translation on part-of-speech and semantic tagging tasks](https://md.research.elamur.ai/free/en/papers/belinkov-2018-evaluating-layers-representation-neural-machine/). In Proceedings of the Eighth International Joint Conference on Natural Language Process…
8. Alexis Conneau, German Kruszewski, Guillaume Lample, Loı̈c Barrault, and Marco Baroni. 2018. [What you can cram into a single $&!\#* vector: Probing sentence embeddings for linguistic properties](https://md.research.elamur.ai/free/en/papers/conneau-2018-what-you-can-cram-into/). In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long…
9. Davide Biasion, Alessandro Fabris, Gianmaria Silvello, and Gian Antonio Susto. 2020. Gender bias in italian word embeddings. In Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. [BERT: Pre-training of deep bidirectional transformers for language understanding](https://md.research.elamur.ai/free/en/papers/devlin-2019-bert-pre-training-deep-bidirectional/). In Proceedings of…
10. Hila Gonen, Yova Kementchedjhieva, and Yoav Goldberg. 2019. How does grammatical gender affect noun representations in gender-marking languages? In Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL), pages 463–471, Hong Kong, China. Association for Computational Li… [find](https://scholar.google.com/scholar?q=Hila+Gonen%2C+Yova+Kementchedjhieva%2C+and+Yoav+Goldberg%2E+2019%2E+How+does+grammatical+gender+affect+noun+representations+in+gender%2Dmarking+languages%3F+In+Proceedings+of+the+23rd+Conference+on+Computational+)
11. Yanai Elazar, Shauli Ravfogel, Alon Jacovi, and Yoav Goldberg. 2021. [Amnesic probing: Behavioral explanation with amnesic counterfactuals](https://md.research.elamur.ai/free/en/papers/elazar-2021-amnesic-probing-behavioral-explanation-amnesic/). Transactions of the Association for Computational Linguistics. https://doi.org/10.1162/tacl_a_00359 [↗](https://doi.org/10.1162/tacl_a_00359)
12. Hila Gonen, Shauli Ravfogel, and Yoav Goldberg. 2022. Analyzing gender representation in multilingual models. In Proceedings of the 7th Workshop on Representation Learning for NLP, pages 67–77, Dublin, Ireland. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Hila+Gonen%2C+Shauli+Ravfogel%2C+and+Yoav+Goldberg%2E+2022%2E+Analyzing+gender+representation+in+multilingual+models%2E+In+Proceedings+of+the+7th+Workshop+on+Representation+Learning+for+NLP%2C+pages+67%E2%80%9377%2C+Dublin)
13. Allyson Ettinger, Ahmed Elgohary, and Philip Resnik. 2016. [Probing for semantic evidence of composition by means of simple classification tasks](https://md.research.elamur.ai/free/en/papers/ettinger-2016-probing-semantic-evidence-composition-means/). In Proceedings of the 1st Workshop on Evaluating Vector-Space Representations for NLP, pages 134–139, Berlin, Germany. Association for Computational Lingui…
14. Aitor Gonzalez-Agirre, Egoitz Laparra, and German Rigau. 2012. Multilingual central repository version 3.0. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12), pages 2525–2529, Istanbul, Turkey. European Language Resources Association (ELRA). [find](https://scholar.google.com/scholar?q=Aitor+Gonzalez%2DAgirre%2C+Egoitz+Laparra%2C+and+German+Rigau%2E+2012%2E+Multilingual+central+repository+version+3%2E0%2E+In+Proceedings+of+the+Eighth+International+Conference+on+Language+Resources+and+Evaluation+%28)
15. 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, 47(2):333–386. https://doi.org/10.1162/coli_a_00404 [↗](https://doi.org/10.1162/coli_a_00404)
16. M. A. Hernán and J. M. Robins. 2020. Causal inference: What if. Boca Raton, FL: Chapman & Hall/CRC. [find](https://scholar.google.com/scholar?q=M%2E+A%2E+Herna%CC%81n+and+J%2E+M%2E+Robins%2E+2020%2E+Causal+inference%3A+What+if%2E+Boca+Raton%2C+FL%3A+Chapman+%26+Hall%2FCRC%2E)
17. John Hewitt, Kawin Ethayarajh, Percy Liang, and Christopher Manning. 2021. Conditional probing: Measuring usable information beyond a baseline. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 1626–1639, Online and Punta Cana, Dominican Republic. Assoc… [find](https://scholar.google.com/scholar?q=John+Hewitt%2C+Kawin+Ethayarajh%2C+Percy+Liang%2C+and+Christopher+Manning%2E+2021%2E+Conditional+probing%3A+Measuring+usable+information+beyond+a+baseline%2E+In+Proceedings+of+the+2021+Conference+on+Empirical+Metho)
18. Matthew Finlayson, Aaron Mueller, Sebastian Gehrmann, Stuart Shieber, Tal Linzen, and Yonatan Belinkov. 2021. Causal analysis of syntactic agreement mechanisms in neural language models. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th Internati… [find](https://scholar.google.com/scholar?q=Matthew+Finlayson%2C+Aaron+Mueller%2C+Sebastian+Gehrmann%2C+Stuart+Shieber%2C+Tal+Linzen%2C+and+Yonatan+Belinkov%2E+2021%2E+Causal+analysis+of+syntactic+agreement+mechanisms+in+neural+language+models%2E+In+Proceeding)
19. John Hewitt and Percy Liang. 2019. Designing and interpreting probes with control tasks. 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 2733–2743, Hong Kong, Chi… [find](https://scholar.google.com/scholar?q=John+Hewitt+and+Percy+Liang%2E+2019%2E+Designing+and+interpreting+probes+with+control+tasks%2E+In+Proceedings+of+the+2019+Conference+on+Empirical+Methods+in+Natural+Language+Processing+and+the+9th+Internati)
20. Mario Giulianelli, Jack Harding, Florian Mohnert, Dieuwke Hupkes, and Willem Zuidema. 2018. Under the hood: Using diagnostic classifiers to investigate and improve how language models track agreement information. In Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neura… [find](https://scholar.google.com/scholar?q=Mario+Giulianelli%2C+Jack+Harding%2C+Florian+Mohnert%2C+Dieuwke+Hupkes%2C+and+Willem+Zuidema%2E+2018%2E+Under+the+hood%3A+Using+diagnostic+classifiers+to+investigate+and+improve+how+language+models+track+agreement+)
21. Dieuwke Hupkes, Sara Veldhoen, and Willem Zuidema. 2018. Visualisation and ‘diagnostic classifiers’ reveal how recurrent and recursive neural networks process hierarchical structure. Journal of Artificial Intelligence Research, 61:907–926. https://doi.org/10.1613/jair.1.11196 — [doi:10.1613/jair.1.11196](https://doi.org/10.1613/jair.1.11196) [↗](https://doi.org/10.1613/jair.1.11196)
22. Joakim Nivre, Marie-Catherine de Marneffe, Filip Ginter, Jan Hajič, Christopher D. Manning, Sampo Pyysalo, Sebastian Schuster, Francis Tyers, and Daniel Zeman. 2020. [Universal Dependencies v2: An evergrowing multilingual treebank collection](https://md.research.elamur.ai/free/en/papers/nivre-2020-universal-dependencies-v2/). In Proceedings of the 12th Language Resources and Evaluat…
23. Mandar Joshi, Omer Levy, Luke Zettlemoyer, and Daniel Weld. 2019. [BERT for coreference resolution: Baselines and analysis](https://md.research.elamur.ai/free/en/papers/joshi-2019-bert-coreference-resolution-baselines-analysis/). 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…
24. Judea Pearl. 2009. Causal inference in statistics: An overview. Statistics Surveys, 3:96–146. https://doi.org/10.1214/09-SS057 [↗](https://doi.org/10.1214/09-SS057)
25. Tiago Pimentel and Ryan Cotterell. 2021. A Bayesian framework for information-theoretic probing. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 2869–2887, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Tiago+Pimentel+and+Ryan+Cotterell%2E+2021%2E+A+Bayesian+framework+for+information%2Dtheoretic+probing%2E+In+Proceedings+of+the+2021+Conference+on+Empirical+Methods+in+Natural+Language+Processing%2C+pages+2869%E2%80%932)
26. Dan Kondratyuk. 2019. Cross-lingual lemmatization and morphology tagging with two-stage multilingual BERT fine-tuning. In Proceedings of the 16th Workshop on Computational Research in Phonetics, Phonology, and Morphology, pages 12–18, Florence, Italy. Association for Computational Linguistics. https… [find](https://scholar.google.com/scholar?q=Dan+Kondratyuk%2E+2019%2E+Cross%2Dlingual+lemmatization+and+morphology+tagging+with+two%2Dstage+multilingual+BERT+fine%2Dtuning%2E+In+Proceedings+of+the+16th+Workshop+on+Computational+Research+in+Phonetics%2C+Phono)
27. Tiago Pimentel, Naomi Saphra, Adina Williams, and Ryan Cotterell. 2020a. Pareto probing: Trading off accuracy for complexity. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 3138–3153, Online. Association for Computational Linguistics. https:/… [find](https://scholar.google.com/scholar?q=Tiago+Pimentel%2C+Naomi+Saphra%2C+Adina+Williams%2C+and+Ryan+Cotterell%2E+2020a%2E+Pareto+probing%3A+Trading+off+accuracy+for+complexity%2E+In+Proceedings+of+the+2020+Conference+on+Empirical+Methods+in+Natural+Lang)
28. Karim Lasri, Tiago Pimentel, Alessandro Lenci, Thierry Poibeau, and Ryan Cotterell. 2022. Probing for the usage of grammatical number. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 8818–8831, Dublin, Ireland. Association for… [find](https://scholar.google.com/scholar?q=Karim+Lasri%2C+Tiago+Pimentel%2C+Alessandro+Lenci%2C+Thierry+Poibeau%2C+and+Ryan+Cotterell%2E+2022%2E+Probing+for+the+usage+of+grammatical+number%2E+In+Proceedings+of+the+60th+Annual+Meeting+of+the+Association+for+)
29. Tiago Pimentel, Josef Valvoda, Rowan Hall Maudslay, Ran Zmigrod, Adina Williams, and Ryan Cotterell. 2020b. [Information-theoretic probing for linguistic structure](https://md.research.elamur.ai/free/en/papers/pimentel-2020-information-theoretic-probing-linguistic-structure/). In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 4609–4622, Online. Association for Com…
30. Paul Pu Liang, Irene Mengze Li, Emily Zheng, Yao Chong Lim, Ruslan Salakhutdinov, and Louis-Philippe Morency. 2020. [Towards debiasing sentence representations](https://md.research.elamur.ai/free/en/papers/liang-2020-debiasing-sentence-representations/). In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 5502–5515, Online. Association for Computa…
31. Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, and Ilya Sutskever. 2019. Language models are unsupervised multitask learners. OpenAI blog, 1(8):9. [find](https://scholar.google.com/scholar?q=Alec+Radford%2C+Jeffrey+Wu%2C+Rewon+Child%2C+David+Luan%2C+Dario+Amodei%2C+and+Ilya+Sutskever%2E+2019%2E+Language+models+are+unsupervised+multitask+learners%2E+OpenAI+blog%2C+1%288%29%3A9%2E)
32. RyanMcDonald, JoakimNivre, Yvonne Quirmbach-Brundage, Yoav Goldberg, Dipanjan Das, Kuzman Ganchev, Keith Hall, Slav Petrov, Hao Zhang, Oscar Täckström, Claudia Bedini, Núria Bertomeu Castelló, and Jungmee Lee. 2013. [Universal Dependency annotation for multilingual parsing](https://md.research.elamur.ai/free/en/papers/mcdonald-2013-universal-dependency-annotation-multilingual-parsing/). In Proceedings of the…
33. Shauli Ravfogel, Yanai Elazar, Hila Gonen, Michael Twiton, and Yoav Goldberg. 2020. [Null it out: Guarding protected attributes by iterative nullspace projection](https://md.research.elamur.ai/free/en/papers/ravfogel-2020-null-it-out-guarding-protected/). In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 7237–7256, Online. Association for Compu…
34. Shauli Ravfogel, Grusha Prasad, Tal Linzen, and Yoav Goldberg. 2021. Counterfactual interventions reveal the causal effect of relative clause representations on agreement prediction. In Proceedings of the 25th Conference on Computational Natural Language Learning, pages 194–209, Online. Association… [find](https://scholar.google.com/scholar?q=Shauli+Ravfogel%2C+Grusha+Prasad%2C+Tal+Linzen%2C+and+Yoav+Goldberg%2E+2021%2E+Counterfactual+interventions+reveal+the+causal+effect+of+relative+clause+representations+on+agreement+prediction%2E+In+Proceedings+of)
35. Mariona Taulé, M. Antònia Martı́, and Marta Recasens. 2008. AnCora: Multilevel annotated corpora for Catalan and Spanish. In Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08), Marrakech, Morocco. European Language Resources Association (ELRA). [find](https://scholar.google.com/scholar?q=Mariona+Taule%CC%81%2C+M%2E+Anto%CC%80nia+Mart%C4%B1%CC%81%2C+and+Marta+Recasens%2E+2008%2E+AnCora%3A+Multilevel+annotated+corpora+for+Catalan+and+Spanish%2E+In+Proceedings+of+the+Sixth+International+Conference+on+Language+Resources+a)
36. Shauli Ravfogel, Michael Twiton, Yoav Goldberg, and Ryan Cotterell. 2022a. Linear relaxed adversarial concept erasure. [find](https://scholar.google.com/scholar?q=Shauli+Ravfogel%2C+Michael+Twiton%2C+Yoav+Goldberg%2C+and+Ryan+Cotterell%2E+2022a%2E+Linear+relaxed+adversarial+concept+erasure%2E)
37. Shauli Ravfogel, FranciscoVargas, Yoav Goldberg, and Ryan Cotterell. 2022b. Adversarial concept erasure in kernel space. [find](https://scholar.google.com/scholar?q=Shauli+Ravfogel%2C+FranciscoVargas%2C+Yoav+Goldberg%2C+and+Ryan+Cotterell%2E+2022b%2E+Adversarial+concept+erasure+in+kernel+space%2E)
38. Abhilasha Ravichander, Yonatan Belinkov, and Eduard Hovy. 2021. [Probing the probing paradigm: Does probing accuracy entail task relevance?](https://md.research.elamur.ai/free/en/papers/ravichander-2021-probing-probing-paradigm-does-probing/) In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 3363–3377, Online. Association…
39. Paul R. Rosenbaum and Donald B. Rubin. 1983. The central role of the propensity score in observational studies for causal effects. Biometrika, 70(1):41–55. https://doi.org/10.1093/biomet/70.1.41 — [doi:10.1093/biomet/70.1.41](https://doi.org/10.1093/biomet/70.1.41) [↗](https://doi.org/10.1093/biomet/70.1.41)
40. Mycal Tucker, Peng Qian, and Roger Levy. 2021. What if this modified that? Syntactic interventions with counterfactual embeddings. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 862–875, Online. Association for Computational Linguistics. https://doi.org/10.18653… [find](https://scholar.google.com/scholar?q=Mycal+Tucker%2C+Peng+Qian%2C+and+Roger+Levy%2E+2021%2E+What+if+this+modified+that%3F+Syntactic+interventions+with+counterfactual+embeddings%2E+In+Findings+of+the+Association+for+Computational+Linguistics%3A+ACL%2DIJC)
41. 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. [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)
42. Elena Voita and Ivan Titov. 2020. [Information-theoretic probing with minimum description length](https://md.research.elamur.ai/free/en/papers/voita-2020-information-theoretic-probing-minimum-description/). In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 183–196, Online. Association for Computational Linguistics.
43. Rachel Rudinger, Jason Naradowsky, Brian Leonard, and Benjamin Van Durme. 2018. [Gender bias in coreference resolution](https://md.research.elamur.ai/free/en/papers/rudinger-2018-gender-bias-coreference-resolution/). In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), pages 8–1…
44. Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Clement Delangue, Anthony Moi, Pierric 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… — [Transformers: State-of-the-Art Natural Language Processing](https://md.research.elamur.ai/free/en/papers/wolf-2020-transformers-state-art-natural-language/)
45. Naomi Saphra and Adam Lopez. 2019. [Understanding learning dynamics of language models with SVCCA](https://md.research.elamur.ai/free/en/papers/saphra-2019-understanding-learning-dynamics-language-models/). In 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), pages 3257–3267, Minn…
46. Gabriel Stanovsky, Noah A. Smith, and Luke Zettlemoyer. 2019. Evaluating gender bias in Rowan Zellers, Ari Holtzman, Yonatan Bisk, Ali Farhadi, and Yejin Choi. 2019. HellaSwag: Can a machine really finish your sentence? In Proceedings of the 57th Annual Meeting of the Association for Computational L… [find](https://scholar.google.com/scholar?q=Gabriel+Stanovsky%2C+Noah+A%2E+Smith%2C+and+Luke+Zettlemoyer%2E+2019%2E+Evaluating+gender+bias+in+Rowan+Zellers%2C+Ari+Holtzman%2C+Yonatan+Bisk%2C+Ali+Farhadi%2C+and+Yejin+Choi%2E+2019%2E+HellaSwag%3A+Can+a+machine+really+fi)
47. Linguistics: Human Language Technologies, Volume 2 (Short Papers), pages 15–20, New Orleans, Louisiana. Association for Computational Linguistics. https://doi.org/10 .18653/v1/N18-2003 — [Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods](https://md.research.elamur.ai/free/en/papers/zhao-2018-gender-bias-coreference-resolution-evaluation/)
48. Ran Zmigrod, Sabrina J. Mielke, Hanna Wallach, and Ryan Cotterell. 2019. [Counterfactual data augmentation for mitigating gender stereotypes in languages with rich morphology](https://md.research.elamur.ai/free/en/papers/zmigrod-2019-counterfactual-data-augmentation-mitigating-gender/). In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 1651–1661, Florence, Italy.…
49. Jieyu Zhao, Tianlu Wang, Mark Yatskar, Vicente Ordonez, and Kai-Wei Chang. 2018. [Gender bias in coreference resolution: Evaluation and debiasing methods](https://md.research.elamur.ai/free/en/papers/zhao-2018-gender-bias-coreference-resolution-evaluation/). In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational

*Updated 30 October 2026*