syntactic generalization

GiLT: Augmenting Transformer Language Models with Dependency Graphs ACL 2026 A Systematic Study of Compositional Syntactic Transformer Language Models ACL 2025 Between Circuits and Chomsky: Pre-pretraining on Formal Languages Imparts Linguistic Biases ACL 2025 Does Vision Accelerate Hierarchical Generalization in Neural Language Learners? COLING 2025 Mind the Gap: How BabyLMs Learn Filler-Gap Dependencies EMNLP 2025 Sneaking Syntax into Transformer Language Models with Tree Regularization NAACL 2025 Unpacking Let Alone: Human-Scale Models Generalize to a Rare Construction in Form but not Meaning EMNLP 2025 Can Language Models Induce Grammatical Knowledge from Indirect Evidence? EMNLP 2024 Language Models Learn Rare Phenomena from Less Rare Phenomena: The Case of the Missing AANNs EMNLP 2024 Semantic Training Signals Promote Hierarchical Syntactic Generalization in Transformers EMNLP 2024 The Heuristic Core: Understanding Subnetwork Generalization in Pretrained Language Models ACL 2024 Analyzing Syntactic Generalization Capacity of Pre-trained Language Models on Japanese Honorific Conversion ACL 2023 BLM-s/lE: A structured dataset of English spray-load verb alternations for testing generalization in LLMs EMNLP 2023 How Well Do Text Embedding Models Understand Syntax? EMNLP 2023 Pushdown Layers: Encoding Recursive Structure in Transformer Language Models EMNLP 2023 Syntax and Geometry of Information ACL 2023 Coloring the Blank Slate: Pre-training Imparts a Hierarchical Inductive Bias to Sequence-to-sequence Models ACL 2022 Composition, Attention, or Both? EMNLP 2022 Does BERT really agree ? Fine-grained Analysis of Lexical Dependence on a Syntactic Task ACL 2022 Enhancing the Transformer Decoder with Transition-based Syntax CoNLL 2022 The Paradox of the Compositionality of Natural Language: A Neural Machine Translation Case Study ACL 2022 Controlled Evaluation of Grammatical Knowledge in Mandarin Chinese Language Models EMNLP 2021 Explicitly Modeling Syntax in Language Models with Incremental Parsing and a Dynamic Oracle NAACL 2021 How much pretraining data do language models need to learn syntax? EMNLP 2021 Structural Guidance for Transformer Language Models ACL 2021