mlsanityData to 7 Oct 2026

Using Priming to Uncover the Organization of Syntactic Representations in Neural Language Models

arXiv 1909.10579 ↗First posted 23 Sep 2019cs.CLcited by 29

Not on the map. Why?

Abstract (arXiv)

Neural language models (LMs) perform well on tasks that require sensitivity to syntactic structure. Drawing on the syntactic priming paradigm from psycholinguistics, we propose a novel technique to analyze the representations that enable such success. By establishing a gradient similarity metric between structures, this technique allows us to reconstruct the organization of the LMs' syntactic representational space. We use this technique to demonstrate that LSTM LMs' representations of different types of sentences with relative clauses are organized hierarchically in a linguistically interpretable manner, suggesting that the LMs track abstract properties of the sentence.

Key facts. Cited by 29 papers in the map (data through 7 Oct 2026). First posted on arXiv 23 Sep 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 4; 2023: 6; 2024: 10; 2025: 4; 2026: 2.

29 papers.

Sort:

By area:

  1. 2021Counterfactual Interventions Reveal the Causal Effect of Relative Clause Representations on Agreement Predictioncited by 58
  2. 2021Structural Persistence in Language Models: Priming as a Window into Abstract Language Representationscited by 44
  3. 2022Can language models handle recursively nested grammatical structures? A case study on comparing models and humanscited by 41
  4. 2023Modeling rapid language learning by distilling Bayesian priors into artificial neural networkscited by 40
  5. 2024Filtered Corpus Training (FiCT) Shows that Language Models can Generalize from Indirect Evidencecited by 35
  6. 2023Do large language models resemble humans in language use?cited by 34
  7. 2024Mission: Impossible Language Modelscited by 31
  8. 2022Neural reality of argument structure constructionscited by 25
  9. 2022Language model acceptability judgements are not always robust to contextcited by 22
  10. 2024Do Language Models Exhibit Human-like Structural Priming Effects?cited by 21
  11. 2025Causal Interventions Reveal Shared Structure Across English Filler-Gap Constructionscited by 21
  12. 2023Machine Psychologycited by 16
17 more
  1. 2023Structural Priming Demonstrates Abstract Grammatical Representations in Multilingual Language Modelscited by 16
  2. 2024Generalizations across filler-gap dependencies in neural language modelscited by 12
  3. 2024Rolling the DICE on Idiomaticity: How LLMs Fail to Grasp Contextcited by 11
  4. 2025On the Acquisition of Shared Grammatical Representations in Bilingual Language Modelscited by 7
  5. 2021Uncovering Constraint-Based Behavior in Neural Models via Targeted Fine-Tuningcited by 5
  6. 2022Collateral facilitation in humans and language modelscited by 5
  7. 2024Interpretability of Language Models via Task Spacescited by 4
  8. 2024SPAWNing Structural Priming Predictions from a Cognitively Motivated Parsercited by 3
  9. 2024Modeling Bilingual Sentence Processing: Evaluating RNN and Transformer Architectures for Cross-Language Structural Primingcited by 3
  10. 2024Is In-Context Learning a Type of Error-Driven Learning? Evidence from the Inverse Frequency Effect in Structural Primingcited by 3
  11. 2024Investigating Idiomaticity in Word Representationscited by 1
  12. 2023Multimodal Shannon Game with Imagescited by 0
  13. 2023Crosslingual Structural Priming and the Pre-Training Dynamics of Bilingual Language Modelscited by 0
  14. 2025Towards Human Cognition: Visual Context Guides Syntactic Priming in Fusion-Encoded Modelscited by 0
  15. 2025Multilingual Relative Clause Attachment Ambiguity Resolution in Large Language Modelscited by 0
  16. 2026Causal Drawbridges: Characterizing Gradient Blocking of Syntactic Islands in Transformer LMscited by 0
  17. 2026Filling in the Mechanisms: How do LMs Learn Filler-Gap Dependencies under Developmental Constraints?cited by 0