mlsanityData to 14 Oct 2026

Naturalistic Causal Probing for Morpho-Syntax

arXiv 2205.07043 ↗First posted 14 May 2022cs.CLcited by 19

Not on the map. Why?

Abstract (arXiv)

Probing has become a go-to methodology for interpreting and analyzing deep neural models in natural language processing. However, there is still a lack of understanding of the limitations and weaknesses of various types of probes. In this work, we suggest a strategy for input-level intervention on naturalistic sentences. Using our approach, we intervene on the morpho-syntactic features of a sentence, while keeping the rest of the sentence unchanged. Such an intervention allows us to causally probe pre-trained models. We apply our naturalistic causal probing framework to analyze the effects of grammatical gender and number on contextualized representations extracted from three pre-trained models in Spanish: the multilingual versions of BERT, RoBERTa, and GPT-2. Our experiments suggest that naturalistic interventions lead to stable estimates of the causal effects of various linguistic properties. Moreover, our experiments demonstrate the importance of naturalistic causal probing when analyzing pre-trained models.

Key facts. Cited by 19 papers in the map (data through 14 Oct 2026). Builds on 32 of its 55 references that are in the map. First posted on arXiv 14 May 2022.

Builds on

32 of 55 references.

References · 32

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2019HellaSwag: Can a Machine Really Finish Your Sentence?cited by 4,100
  4. 2016Understanding intermediate layers using linear classifier probescited by 1,353
  5. 2016Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddingscited by 1,312
  6. 2018Gender Bias in Coreference Resolution: Evaluation and Debiasing Methodscited by 659
  7. 2019Designing and Interpreting Probes with Control Taskscited by 640
  8. 2018What you can cram into a single vector: Probing sentence embeddings for linguistic propertiescited by 457
  9. 2020Null It Out: Guarding Protected Attributes by Iterative Nullspace Projectioncited by 455
  10. 2018Gender Bias in Coreference Resolutioncited by 442
  11. 2020Universal Dependencies v2: An Evergrowing Multilingual Treebank Collectioncited by 271
  12. 2019Evaluating Gender Bias in Machine Translationcited by 249
20 more
  1. 2020Information-Theoretic Probing with Minimum Description Lengthcited by 232
  2. 2020Information-Theoretic Probing for Linguistic Structurecited by 207
  3. 2019Counterfactual Data Augmentation for Mitigating Gender Stereotypes in Languages with Rich Morphologycited by 200
  4. 2020Towards Debiasing Sentence Representationscited by 171
  5. 2020Probing the Probing Paradigm: Does Probing Accuracy Entail Task Relevance?cited by 151
  6. 2021Causal Analysis of Syntactic Agreement Mechanisms in Neural Language Modelscited by 131
  7. 2019BERT for Coreference Resolution: Baselines and Analysiscited by 125
  8. 2020CausaLM: Causal Model Explanation Through Counterfactual Language Modelscited by 117
  9. 2018Under the Hood: Using Diagnostic Classifiers to Investigate and Improve how Language Models Track Agreement Informationcited by 97
  10. 2020Unmasking Contextual Stereotypes: Measuring and Mitigating BERT's Gender Biascited by 82
  11. 2021Conditional probing: measuring usable information beyond a baselinecited by 62
  12. 2021Counterfactual Interventions Reveal the Causal Effect of Relative Clause Representations on Agreement Predictioncited by 59
  13. 2022Probing for the Usage of Grammatical Numbercited by 59
  14. 2018Evaluating Layers of Representation in Neural Machine Translation on Part-of-Speech and Semantic Tagging Taskscited by 56
  15. 2020Pareto Probing: Trading Off Accuracy for Complexitycited by 55
  16. 2022Kernelized Concept Erasurecited by 48
  17. 2021What if This Modified That? Syntactic Interventions via Counterfactual Embeddingscited by 39
  18. 2021A Bayesian Framework for Information-Theoretic Probingcited by 22
  19. 2019How does Grammatical Gender Affect Noun Representations in Gender-Marking Languages?cited by 14
  20. 2022Analyzing Gender Representation in Multilingual Modelscited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 2; 2023: 3; 2024: 7; 2025: 6; 2026: 1.

19 papers.

Sort:

By area:

  1. 2024ReFT: Representation Finetuning for Language Modelscited by 197
  2. 2022Towards Faithful Model Explanation in NLP: A Surveycited by 130
  3. 2022State-of-the-art generalisation research in NLP: A taxonomy and reviewcited by 98
  4. 2025MIB: A Mechanistic Interpretability Benchmarkcited by 56
  5. 2024LLaVA Steering: Visual Instruction Tuning with 500x Fewer Parameters through Modality Linear Representation-Steeringcited by 51
  6. 2024CausalGym: Benchmarking causal interpretability methods on linguistic taskscited by 46
  7. 2023A Geometric Notion of Causal Probingcited by 25
  8. 2024On Behalf of the Stakeholders: Trends in NLP Model Interpretability in the Era of LLMscited by 25
  9. 2024The Quest for the Right Mediator: Surveying Mechanistic Interpretability Through the Lens of Causal Mediation Analysiscited by 24
  10. 2023From Neural Activations to Concepts: A Survey on Explaining Concepts in Neural Networkscited by 13
  11. 2023Probing Graph Representationscited by 10
  12. 2025Linguistic Generalizations are not Rules: Impacts on Evaluation of LMscited by 10
7 more
  1. 2025Linguistic Interpretability of Transformer-based Language Models: a systematic reviewcited by 7
  2. 2025Analyzing the Inner Workings of Transformers in Compositional Generalizationcited by 6
  3. 2024Probing the Category of Verbal Aspect in Transformer Language Modelscited by 5
  4. 2024Latent Causal Probing: A Formal Perspective on Probing with Causal Models of Datacited by 1
  5. 2025On Representational Dissociation of Language and Arithmetic in Large Language Modelscited by 1
  6. 2025Findings of the BlackboxNLP 2025 Shared Task: Localizing Circuits and Causal Variables in Language Modelscited by 1
  7. 2026The Grammar of Transformers: A Systematic Review of Interpretability Research on Syntactic Knowledge in Language Modelscited by 1