The DOI matches its Crossref record; 44 of the 46 references it cites were found in a registry or an index.
Targeted Syntactic Evaluation of Language Models
Open accessAbstract
We present a dataset for evaluating the grammaticality of the predictions of a language model.We automatically construct a large number of minimally different pairs of English sentences, each consisting of a grammatical and an ungrammatical sentence.The sentence pairs represent different variations of structure-sensitive phenomena: subject-verb agreement, reflexive anaphora and negative polarity items.We expect a language model to assign a higher probability to the grammatical sentence than the ungrammatical one.In an experiment using this data set, an LSTM language model performed poorly on many of the constructions.Multi-task training with a syntactic objective (CCG supertagging) improved the LSTM's accuracy, but a large gap remained between its performance and the accuracy of human participants recruited online.This suggests that there is considerable room for improvement over LSTMs in capturing syntax in a language model.
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.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“BLiMP, and other related syntactic benchmarks such as those presented in Marvin and Linzen (2018) and Gauthier et al. (2020), were specifically designed to mimic the types of tests invented by linguists and cognitive scientists to reveal syntactic competence-i.e., they are all based on minimal pair sentences.”
From Findings of the BabyLM Challenge: Sample-Efficient Pretraining on Developmentally Plausible Corpora (2023) · cites this paper as Marvin and Linzen (2018)
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
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
Elman, J. L. (1990) · Cognitive Science · doi:10.1207/s15516709cog1402_1 · Cited by 11,212
Recurrent neural network based language model
Mikolov, T., Karafiát, M., Burget, L., Černocký, J., & Khudanpur, S. (2010) · Interspeech 2010 · doi:10.21437/interspeech.2010-343 · Cited by 5,390
SRILM - an extensible language modeling toolkit
Stolcke, A. (2002) · International Conference on Spoken Language Processing (ICSLP) · doi:10.21437/icslp.2002-303 · Cited by 4,385
Neural Network Acceptability Judgments
Warstadt, A., Singh, A., & Bowman, S. R. (2019) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00290 · Cited by 1,215
Assessing the Ability of LSTMs to Learn Syntax-Sensitive Dependencies
Linzen, T., Emmanuel Dupoux, A., & Goldberg, Y. (2016) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00115 · Cited by 820
Self-citationAgreement attraction in comprehension: Representations and processes
WAGERS, M. W., Lau, E. F., & Phillips, C. (2009) · Journal of Memory and Language · doi:10.1016/j.jml.2009.04.002 · Cited by 639
Bock, K., & Miller, C. (1991) · Cognitive Psychology · doi:10.1016/0010-0285(91)90003-7 · Cited by 558
Colorless Green Recurrent Networks Dream Hierarchically
Gulordava, K., Bojanowski, P., Grave, É., Linzen, T., & Baroni, M. (2018) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/n18-1108 · Cited by 538
Self-citation
Research works printed but not linked: 2
- Anastasia Giannakidou. 2011. Negative and positive polarity items: Variation, licensing, and composi- tionality. In Semantics: An international hand- book of natural language meaning, pages 1660- 1712. Berlin: Mouton de Gruyter.
- Bingley, U.K.: Emerald.
Cited by
Sorted by citations
Items 301–332 of 332
Variation and generality in encoding of syntactic anomaly information in sentence embeddings
Wu, Q., & Ettinger, A. (2021) · BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP (BlackboxNLP) · doi:10.18653/v1/2021.blackboxnlp-1.18
Evaluating the Morphosyntactic Well-formedness of Generated TextsPreprint
Pratapa, A., Anastasopoulos, A., Rijhwani, S., Chaudhary, A., Mortensen, D. R., Neubig, G., & Tsvetkov, Y. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.16590
How much pretraining data do language models need to learn syntax?Preprint
Pérez-Mayos, L., Ballesteros, M., & Wanner, L. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.03160 · Cited by 5
Multilingual Syntax-aware Language Modeling through Dependency Tree Conversion
Kando, S., Noji, H., & Miyao, Y. (2022) · Workshop on Structured Prediction for NLP (SPNLP) · doi:10.18653/v1/2022.spnlp-1.1
Sun, S., Dillon, B., & Iyyer, M. (2022) · Workshop on Insights from Negative Results in NLP (Insights) · doi:10.18653/v1/2022.insights-1.6
(2022) · Linköping electronic conference proceedings · doi:10.3384/ecp190
Syntax and Geometry of Information
Bailly, R., Leblond, L., & Gábor, K. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-long.590
Analyzing Text Representations by Measuring Task Alignment
González-Gutiérrez, C., Primadhanty, A., Cazzaro, F., & Quattoni, A. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-short.7
BUMP: A Benchmark of Unfaithful Minimal Pairs for Meta-Evaluation of Faithfulness Metrics
Ma, L., Cao, S., Logan, R. L., Lu, D., Ran, S., Zhang, K., Tetreault, J., & Jaimes, A. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-long.716 · Cited by 3
How Much Syntactic Supervision is “Good Enough”?
Noji, H., & Oseki, Y. (2023) · Findings of the Association for Computational Linguistics: EACL · doi:10.18653/v1/2023.findings-eacl.173
Beinborn, L., & Hollenstein, N. (2023) · Synthesis lectures on human language technologies · doi:10.1007/978-3-031-43260-6_4
Towards Immersive Computational Storytelling:Card-Framework for Enhanced Persona-Driven DialoguesPreprint
Liao, B., & Vargas, D. V. (2023) · doi:10.36227/techrxiv.24605667
METAPROBE: A Representation- and Task-Agnostic Probe
Zhou, Y., & Srikumar, V. (2023) · BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP (BlackboxNLP) · doi:10.18653/v1/2023.blackboxnlp-1.18
NPIs Aren’t Exactly Easy: Variation in Licensing across Large Language Models
DeCarlo, D., Palmer, W., Wilson, M., & Frank, B. (2023) · BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP (BlackboxNLP) · doi:10.18653/v1/2023.blackboxnlp-1.25
Disentangling the Linguistic Competence of Privacy-Preserving BERT
Arnold, S., Kemmerzell, N., & Schreiner, A. (2023) · BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP (BlackboxNLP) · doi:10.18653/v1/2023.blackboxnlp-1.5
Pushdown Layers: Encoding Recursive Structure in Transformer Language Models
Murty, S., Sharma, P., Andreas, J., & Manning, C. D. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.195 · Cited by 8
Syntactic Substitutability as Unsupervised Dependency Syntax
Jian, J., & Reddy, S. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.144
Toward Visual Syntactical Understanding
Chowdhury, S. S., Chandra, S., & Roy, K. (2024) · IEEE Access · doi:10.1109/access.2024.3397061
Context-biased vs. structure-biased disambiguation of relative clauses in large language models
Issa, E., & Atouf, N. (2024) · Procedia Computer Science · doi:10.1016/j.procs.2024.10.217
(2025) · The MIT Press eBooks · doi:10.7551/mitpress/15811.003.0010
Enabling large language models with explainability
Galitsky, B. A. (2025) · Elsevier eBooks · doi:10.1016/b978-0-443-30046-2.00011-9
Large Language Models Can Participate in Psycholinguistic Testing in Korean
Song, S., & Noh, K. (2025) · Springer eBooks · doi:10.1007/978-3-031-88087-2_14
Inducing Grammatical Knowledge from Indirect Evidence in Language Models
Oba, M., Oseki, Y., Fukatsu, A., Haga, A., Ouchi, H., Watanabe, T., & Sugawara, S. (2026) · Journal of Natural Language Processing · doi:10.5715/jnlp.33.109
Study of the abstraction capabilities of neural language models
Li, B. (2023) · theses.fr (ABES) · doi:10.70675/0236e084zee1ez4013z8f5bz6eebee3f0e4e
Arous, I., Chehbouni, K., Cheng, Z., & Dossou, B. F. P. (2026) · Springer eBooks · doi:10.1007/978-981-95-3658-0_85
Hwang, K. (2026) · The Linguistic Review · doi:10.1515/tlr-2026-0001
Probing English and Spanish Syntax in Language Models
Witty, C., & Sun, C. (2025) · IEEE MIT Undergraduate Research Technology Conference (URTC) · doi:10.1109/urtc68753.2025.11533015
Catasso, N. (2026) · AI-Linguistica Linguistic Studies on AI-Generated Texts and Discourses · doi:10.62408/ai-ling.v3i1.88 · Cited by 1
Kunz, J. (2026) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl.a.727 · Cited by 2
Evaluating the Usage of African-American Vernacular English in Large Language Models
Davis, D., & McCoy, R. T. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-29903-1_15
Patil, T., & Chetia, B. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-20897-2_12
Assessing BERT's Syntactic Abilities
Goldberg, Y. (2019) · arXiv · doi:10.48550/arxiv.1901.05287 · Cited by 385
Metadata
- Authors
- Marvin, R., & Linzen, T.
- Affiliations
- Johns Hopkins University (US)
- Corresponding author
- Linzen, Tal
- ORCID
- Linzen, Tal
- Venue
- Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
- Published
- 2018
- Pages
- 1192-1202
- OpenAlex
- W2888922637
- Cited by
- 334
- References
- 46
- Citations by year
- 2026: 10 · 2025: 15 · 2024: 21 · 2023: 51 · 2022: 38 · 2021: 77 · 2020: 69 · 2019: 51 · 2018: 2
- FWCI
- 20.41
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Conference on Empirical Methods in Natural Language Processing (EMNLP) (publishedVersion, cc-by)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Social Sciences › Arts and Humanities › Language and Linguistics › Syntax, Semantics, Linguistic Variation
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Keywords
- grammaticality judgment, subject-verb agreement, negative polarity items, LSTM language models, human vs machine performance
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
