Disaggregation Reveals Hidden Training Dynamics: The Case of Agreement Attraction

• URL: http://arxiv.org/abs/2510.24934v1
• Date: Tue, 28 Oct 2025 19:59:26 GMT
• Title: Disaggregation Reveals Hidden Training Dynamics: The Case of Agreement Attraction
• Authors: James A. Michaelov, Catherine Arnett,
• Abstract summary: Language models generally produce grammatical text, but they are more likely to make errors in certain contexts.<n>We show that it is possible to better understand the intermediate stages of grammatical learning in language models.<n>We argue that taking this approach to analyzing language model behavior more generally can serve as a powerful tool for understanding the intermediate learning phases, overall training dynamics, and the specific generalizations learned by language models.
• Score: 6.531546527140474
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Language models generally produce grammatical text, but they are more likely to make errors in certain contexts. Drawing on paradigms from psycholinguistics, we carry out a fine-grained analysis of those errors in different syntactic contexts. We demonstrate that by disaggregating over the conditions of carefully constructed datasets and comparing model performance on each over the course of training, it is possible to better understand the intermediate stages of grammatical learning in language models. Specifically, we identify distinct phases of training where language model behavior aligns with specific heuristics such as word frequency and local context rather than generalized grammatical rules. We argue that taking this approach to analyzing language model behavior more generally can serve as a powerful tool for understanding the intermediate learning phases, overall training dynamics, and the specific generalizations learned by language models.

Related papers

• Your Pretrained Model Tells the Difficulty Itself: A Self-Adaptive Curriculum Learning Paradigm for Natural Language Understanding [53.63482987410292]
  We present a self-adaptive curriculum learning paradigm that prioritizes fine-tuning examples based on difficulty scores predicted by pre-trained language models.<n>We evaluate our method on four natural language understanding (NLU) datasets covering both binary and multi-class classification tasks.
  arXiv  Detail & Related papers  (2025-07-13T19:36:17Z)
• Interpretability of Language Models via Task Spaces [14.543168558734001]
  We present an alternative approach to interpret language models (LMs) We focus on the quality of LM processing, with a focus on their language abilities. We construct 'linguistic task spaces' that shed light on the connections LMs draw between language phenomena.
  arXiv  Detail & Related papers  (2024-06-10T16:34:30Z)
• Learning Phonotactics from Linguistic Informants [54.086544221761486]
  Our model iteratively selects or synthesizes a data-point according to one of a range of information-theoretic policies. We find that the information-theoretic policies that our model uses to select items to query the informant achieve sample efficiency comparable to, or greater than, fully supervised approaches.
  arXiv  Detail & Related papers  (2024-05-08T00:18:56Z)
• Counteracts: Testing Stereotypical Representation in Pre-trained Language Models [4.211128681972148]
  We use counterexamples to examine the internal stereotypical knowledge in pre-trained language models (PLMs) We evaluate 7 PLMs on 9 types of cloze-style prompt with different information and base knowledge.
  arXiv  Detail & Related papers  (2023-01-11T07:52:59Z)
• Interpreting Language Models with Contrastive Explanations [99.7035899290924]
  Language models must consider various features to predict a token, such as its part of speech, number, tense, or semantics. Existing explanation methods conflate evidence for all these features into a single explanation, which is less interpretable for human understanding. We show that contrastive explanations are quantifiably better than non-contrastive explanations in verifying major grammatical phenomena.
  arXiv  Detail & Related papers  (2022-02-21T18:32:24Z)
• On The Ingredients of an Effective Zero-shot Semantic Parser [95.01623036661468]
  We analyze zero-shot learning by paraphrasing training examples of canonical utterances and programs from a grammar. We propose bridging these gaps using improved grammars, stronger paraphrasers, and efficient learning methods. Our model achieves strong performance on two semantic parsing benchmarks (Scholar, Geo) with zero labeled data.
  arXiv  Detail & Related papers  (2021-10-15T21:41:16Z)
• Controlled Evaluation of Grammatical Knowledge in Mandarin Chinese Language Models [22.57309958548928]
  We investigate whether structural supervision improves language models' ability to learn grammatical dependencies in typologically different languages. We train LSTMs, Recurrent Neural Network Grammars, Transformer language models, and generative parsing models on datasets of different sizes. We find suggestive evidence that structural supervision helps with representing syntactic state across intervening content and improves performance in low-data settings.
  arXiv  Detail & Related papers  (2021-09-22T22:11:30Z)
• The Grammar-Learning Trajectories of Neural Language Models [42.32479280480742]
  We show that neural language models acquire linguistic phenomena in a similar order, despite having different end performances over the data. Results suggest that NLMs exhibit consistent developmental'' stages.
  arXiv  Detail & Related papers  (2021-09-13T16:17:23Z)
• 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)
• Cross-lingual Spoken Language Understanding with Regularized Representation Alignment [71.53159402053392]
  We propose a regularization approach to align word-level and sentence-level representations across languages without any external resource. Experiments on the cross-lingual spoken language understanding task show that our model outperforms current state-of-the-art methods in both few-shot and zero-shot scenarios.
  arXiv  Detail & Related papers  (2020-09-30T08:56:53Z)
• Recurrent Neural Network Language Models Always Learn English-Like Relative Clause Attachment [17.995905582226463]
  We compare model performance in English and Spanish to show that non-linguistic biases in RNN LMs advantageously overlap with syntactic structure in English but not Spanish. English models may appear to acquire human-like syntactic preferences, while models trained on Spanish fail to acquire comparable human-like preferences.
  arXiv  Detail & Related papers  (2020-05-01T01:21:47Z)
• Data Augmentation for Spoken Language Understanding via Pretrained Language Models [113.56329266325902]
  Training of spoken language understanding (SLU) models often faces the problem of data scarcity. We put forward a data augmentation method using pretrained language models to boost the variability and accuracy of generated utterances.
  arXiv  Detail & Related papers  (2020-04-29T04:07:12Z)

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.