Diverging Transformer Predictions for Human Sentence Processing: A Comprehensive Analysis of Agreement Attraction Effects

[2603.16574] Diverging Transformer Predictions for Human Sentence Processing: A Comprehensive Analysis of Agreement Attraction Effects Skip to main content Search Submit Donate Log in Computer Science > Computation and Language arXiv:2603.16574 (cs) [Submitted on 17 Mar 2026 ( v1 ), last revised 28 Aug 2026 (this version, v2)] Title: Diverging Transformer Predictions for Human Sentence Processing: A Comprehensive Analysis of Agreement Attraction Effects Authors: Titus von der Malsburg , Sebastian Padó View PDF HTML (experimental) Abstract: Transformers underlie almost all state-of-the-art language models in computational linguistics, yet their cognitive adequacy as models of human sentence processing remains disputed. In this work, we use a surprisal-based linking mechanism to systematically evaluate eleven autoregressive transformers of varying sizes and architectures on a more comprehensive set of English agreement attraction configurations than prior work. Our experiments yield mixed results: While transformer predictions generally align with human reading time data for prepositional phrase configurations, performance degrades significantly on object-extracted relative clause configurations. In the latter case, predictions also diverge markedly across models, and no model successfully replicates the asymmetric interference patterns observed in humans. We conclude that current transformer models do not explain human morphosyntactic processing, and that evaluations of transformers as cognitive models must adopt rigorous, comprehensive experimental designs to avoid spurious generalizations from isolated syntactic configurations or individual models. Comments: Paper accepted for EMNLP 2026 main conference Subjects: Computation and Language (cs.CL) Cite as: arXiv:2603.16574 [cs.CL] (or arXiv:2603.16574v2 [cs.CL] for this version) https://doi.org/10.48550/arXiv.2603.16574 Focus to learn more arXiv-issued DOI via DataCite Journal reference: Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing Submission history From: Titus Von Der Malsburg [ view email ] [v1] Tue, 17 Mar 2026 14:27:46 UTC (78 KB) [v2] Fri, 28 Aug 2026 10:08:51 UTC (80 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Additional Features Audio Summary Current browse context: cs.CL < prev | next > new | recent | 2026-03 Change to browse by: cs References & Citations SciX Google Scholar Semantic Scholar export BibTeX citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab)

Related documents

• Diverging Transformer Predictions for Human Sentence Processing: A Comprehensive Analysis of Agreement Attraction Effects#682611
• Syntactic patterns of Italo-Romance CP-layers in Transformers, ChatGPT and Deepseek: two case studies from Romansh and Neapolitan#732119
• Syntactic patterns of Italo-Romance CP-layers in Transformers, ChatGPT and Deepseek: two case studies from Romansh and Neapolitan#107694
• When Cosine Similarity Fails to Reflect Linearly Accessible Structure in Dialogue Models#1037205
• Predicting Turn-Taking Outcomes in Multi-Party Conversation: Interpretable Modelling of Speech and Gaze Dynamics with Interpersonal Closeness#784761