Understanding Syntactic Generalization in Structure-inducing Language Models

• URL: http://arxiv.org/abs/2508.07969v1
• Date: Mon, 11 Aug 2025 13:29:41 GMT
• Title: Understanding Syntactic Generalization in Structure-inducing Language Models
• Authors: David Arps, Hassan Sajjad, Laura Kallmeyer,
• Abstract summary: Structure-inducing Language Models (SiLM) are trained on a self-supervised language modeling task.<n>SiLMs induce a hierarchical sentence representation as a byproduct when processing an input.<n>We study three different SiLM architectures using both natural language (English) corpora and synthetic bracketing expressions.
• Score: 15.419603273515786
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Structure-inducing Language Models (SiLM) are trained on a self-supervised language modeling task, and induce a hierarchical sentence representation as a byproduct when processing an input. A wide variety of SiLMs have been proposed. However, these have typically been evaluated on a relatively small scale, and evaluation of these models has systematic gaps and lacks comparability. In this work, we study three different SiLM architectures using both natural language (English) corpora and synthetic bracketing expressions: Structformer (Shen et al., 2021), UDGN (Shen et al., 2022) and GPST (Hu et al., 2024). We compare them with respect to (i) properties of the induced syntactic representations (ii) performance on grammaticality judgment tasks, and (iii) training dynamics. We find that none of the three architectures dominates across all evaluation metrics. However, there are significant differences, in particular with respect to the induced syntactic representations. The Generative Pretrained Structured Transformer (GPST; Hu et al. 2024) performs most consistently across evaluation settings, and outperforms the other models on long-distance dependencies in bracketing expressions. Furthermore, our study shows that small models trained on large amounts of synthetic data provide a useful testbed for evaluating basic model properties.

Related papers

• Grammaticality Judgments in Humans and Language Models: Revisiting Generative Grammar with LLMs [0.0]
  In traditional generative grammar, systematic contrasts in grammaticality such as subject-auxiliary inversion and the licensing of parasitic gaps are taken as evidence for an internal, hierarchical grammar.<n>We test whether large language models (LLMs), trained only on surface forms, reproduce these contrasts in ways that imply an underlying structural representation.
  arXiv  Detail & Related papers  (2025-12-11T09:17:35Z)
• Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures [49.19753720526998]
  We derive theoretical scaling laws for neural network performance on synthetic datasets.<n>We validate that convolutional networks, whose structure aligns with that of the generative process through locality and weight sharing, enjoy a faster scaling of performance.<n>This finding clarifies the architectural biases underlying neural scaling laws and highlights how representation learning is shaped by the interaction between model architecture and the statistical properties of data.
  arXiv  Detail & Related papers  (2025-05-11T17:44:14Z)
• Towards Human Cognition: Visual Context Guides Syntactic Priming in Fusion-Encoded Models [3.63819860423174]
  Structural priming is a cognitive phenomenon where exposure to a particular syntactic structure increases the likelihood of producing the same structure in subsequent utterances.<n>We introduce PRISMATIC, the first multimodal structural priming dataset.<n>We propose the Syntactic Preservation Index (SPI), a novel reference-free evaluation metric designed specifically to assess structural priming effects in sentence level.
  arXiv  Detail & Related papers  (2025-02-24T21:33:27Z)
• Linguistic Structure Induction from Language Models [1.8130068086063336]
  This thesis focuses on producing constituency and dependency structures from Language Models (LMs) in an unsupervised setting. I present a detailed study on StructFormer (SF) which retrofits a transformer architecture with a encoder network to produce constituency and dependency structures. I present six experiments to analyze and address this field's challenges.
  arXiv  Detail & Related papers  (2024-03-11T16:54:49Z)
• Split and Rephrase with Large Language Models [2.499907423888049]
  Split and Rephrase (SPRP) task consists in splitting complex sentences into a sequence of shorter grammatical sentences. We evaluate large language models on the task, showing that they can provide large improvements over the state of the art on the main metrics.
  arXiv  Detail & Related papers  (2023-12-18T10:16:37Z)
• SLOG: A Structural Generalization Benchmark for Semantic Parsing [68.19511282584304]
  The goal of compositional generalization benchmarks is to evaluate how well models generalize to new complex linguistic expressions. Existing benchmarks often focus on lexical generalization, the interpretation of novel lexical items in syntactic structures familiar from training, are often underrepresented. We introduce SLOG, a semantic parsing dataset that extends COGS with 17 structural generalization cases.
  arXiv  Detail & Related papers  (2023-10-23T15:39:09Z)
• A Machine Learning Approach to Classifying Construction Cost Documents into the International Construction Measurement Standard [0.0]
  We introduce the first automated models for classifying natural language descriptions provided in cost documents called "Bills of Quantities" We learn from a dataset of more than 50 thousand descriptions of items retrieved from 24 large infrastructure construction projects across the United Kingdom.
  arXiv  Detail & Related papers  (2022-10-24T11:35:53Z)
• Model Criticism for Long-Form Text Generation [113.13900836015122]
  We apply a statistical tool, model criticism in latent space, to evaluate the high-level structure of generated text. We perform experiments on three representative aspects of high-level discourse -- coherence, coreference, and topicality. We find that transformer-based language models are able to capture topical structures but have a harder time maintaining structural coherence or modeling coreference.
  arXiv  Detail & Related papers  (2022-10-16T04:35:58Z)
• Compositional Generalization Requires Compositional Parsers [69.77216620997305]
  We compare sequence-to-sequence models and models guided by compositional principles on the recent COGS corpus. We show structural generalization is a key measure of compositional generalization and requires models that are aware of complex structure.
  arXiv  Detail & Related papers  (2022-02-24T07:36:35Z)
• Structural Supervision Improves Few-Shot Learning and Syntactic Generalization in Neural Language Models [47.42249565529833]
  Humans can learn structural properties about a word from minimal experience. We assess the ability of modern neural language models to reproduce this behavior in English.
  arXiv  Detail & Related papers  (2020-10-12T14:12:37Z)
• Learning Universal Representations from Word to Sentence [89.82415322763475]
  This work introduces and explores the universal representation learning, i.e., embeddings of different levels of linguistic unit in a uniform vector space. We present our approach of constructing analogy datasets in terms of words, phrases and sentences. We empirically verify that well pre-trained Transformer models incorporated with appropriate training settings may effectively yield universal representation.
  arXiv  Detail & Related papers  (2020-09-10T03:53:18Z)
• A Systematic Assessment of Syntactic Generalization in Neural Language Models [20.589737524626745]
  We present a systematic evaluation of the syntactic knowledge of neural language models. We find substantial differences in syntactic generalization performance by model architecture. Our results also reveal a dissociation between perplexity and syntactic generalization performance.
  arXiv  Detail & Related papers  (2020-05-07T18:35:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.