The Structural Sources of Verb Meaning Revisited: Large Language Models Display Syntactic Bootstrapping
On the map: Synthetic data and self-improvement for LLMs → LLM synthetic data generation
Abstract (arXiv)
Syntactic bootstrapping (Gleitman, 1990) is the hypothesis that children use the syntactic environments in which a verb occurs to learn its meaning. In this paper, we examine whether large language models exhibit a similar behavior. We do this by training RoBERTa and GPT-2 on perturbed datasets where syntactic information is ablated. Our results show that models' verb representation degrades more when syntactic cues are removed than when co-occurrence information is removed. Furthermore, the representation of mental verbs, for which syntactic bootstrapping has been shown to be particularly crucial in human verb learning, is more negatively impacted in such training regimes than physical verbs. In contrast, models' representation of nouns is affected more when co-occurrences are distorted than when syntax is distorted. In addition to reinforcing the important role of syntactic bootstrapping in verb learning, our results demonstrated the viability of testing developmental hypotheses on a larger scale through manipulating the learning environments of large language models.
Key facts. Cited by 1 paper in the map (data through 13 Oct 2026). Placed in LLM synthetic data generation, one of 13 directions in Synthetic data and self-improvement for LLMs. Builds on 11 of its 38 references that are in the map. First posted on arXiv 17 Aug 2025.
Builds on
11 of 38 references.
References · 11
- 2017Attention Is All You Needcited by 60,106
- 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,322
- 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,360
- 2021Masked Language Modeling and the Distributional Hypothesis: Order Word Matters Pre-training for Littlecited by 176
- 2020Does syntax need to grow on trees? Sources of hierarchical inductive bias in sequence-to-sequence networkscited by 72
- 2024Language Models Learn Rare Phenomena from Less Rare Phenomena: The Case of the Missing AANNscited by 65
- 2023Grokking of Hierarchical Structure in Vanilla Transformerscited by 53
- 2020Can neural networks acquire a structural bias from raw linguistic data?cited by 35
- 2024Filtered Corpus Training (FiCT) Shows that Language Models can Generalize from Indirect Evidencecited by 35
- 2023Visual Grounding Helps Learn Word Meanings in Low-Data Regimescited by 16
- 2024Manipulating language models' training data to study syntactic constraint learning: the case of English passivizationcited by 12
Built on by
Citing papers per year: 2026: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2024Reframing linguistic bootstrapping as joint inference using visually-grounded grammar induction models
- 2026Causal Interventions on Continuous Variables: A Case Study on Verb Bias in Steering Vectors for In-Context Learning
- 2021Syntactic Perturbations Reveal Representational Correlates of Hierarchical Phrase Structure in Pretrained Language Models
- 2026Exposure is Optional: Learning Unlike Coordination in Language Models
- 2026Causal Interventions Reveal Typologically Organized Syntactic Mechanisms in Multilingual Language Models
- 2026Causal Drawbridges: Characterizing Gradient Blocking of Syntactic Islands in Transformer LMs
- 2024From Babbling to Fluency: Evaluating the Evolution of Language Models in Terms of Human Language Acquisition
- 2026Investigating Linguistic Steering: An Analysis of Adjectival Effects Across Large Language Model Architectures