Elamur Research⌕
☰
home / papers / 2026 / Compositional Meaning Representations in LLMs: a Critical Review of Probing Studies

Compositional Meaning Representations in LLMs: a Critical Review of Probing Studies

Summary

LLMs produce language that appears compositional, but it is unclear whether their internal states hold structured meaning representations. This review asks what probing classifiers can reveal about that question. Probing classifiers are lightweight models trained on intermediate-layer activations to recover linguistic properties. The author ran a systematic Google Scholar search, filtered it with inclusion/exclusion criteria, and analysed 24 probing studies. The tasks are sorted into a taxonomy based on the linguistic primitives each presupposes: lexical semantics, syntax–semantics interface, propositional semantics, and discourse/pragmatics.

Evidence weakens as one moves up these tiers. Lexical information is recovered reliably, and sensitivity to sentence-internal structure is uneven. Tasks needing pragmatic inference, speech-act recognition or propositional content give poor results. The author infers that LLM "composition" may rest mainly on lexical and local, distributionally learned regularities rather than full propositional representations. Methodologically, the paper recasts probing as a theory-anchored diagnostic for eliminating implausible compositional mechanisms, not as proof that a representation is actually used.

Key points

  • Selection pipeline: 422 Google Scholar hits were narrowed to 29 studies meeting the criteria (as of February 2026). Full reading left 24 for analysis, and the review does not claim exhaustiveness.
  • The four-tier taxonomy reveals a gradient of evidence: strong for lexical semantics, inconsistent for structural relations, and weak for propositional and discourse-level phenomena.
  • The paper introduces "functional indicativity": decoding a property does not show the model relies on it. Probes can even extract properties from random noise. Proposed remedies include control tasks (Hewitt and Liang, 2019) and amnesic probing (Elazar et al., 2021).
  • Probing is placed at Marr's computational level. Its one-to-many mapping from states to explanations is likened to the Granularity Mismatch Problem (Poeppel and Embick, 2017).
  • Recommended future directions:
    • a bottom-up, model-centred agenda using sparse autoencoder probing (Cunningham et al., 2023);
    • causal intervention and ablation to test functional relevance;
    • usage-based construction approaches as a possibly better theoretical fit;
    • classic probing kept as a post-hoc sanity check.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

Fields: Linguistics & languages

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.starsem-conference.13

@inproceedings{marro2026compositional,
  title = {{Compositional Meaning Representations in LLMs: a Critical Review of Probing Studies}},
  author = {Marro, Rémy},
  booktitle = {Proceedings of the 15th Joint Conference on Lexical and Computational Semantics (*SEM 2026)},
  year = {2026},
  doi = {10.18653/v1/2026.starsem-conference.13},
  url = {https://doi.org/10.18653/v1/2026.starsem-conference.13}
}

References

93 references, 12 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Ehsan Aghazadeh, Mohsen Fayyaz, and Yadollah Yaghoobzadeh. 2022. Metaphors in Pre-Trained Language Models: Probing and Generalization Across Datasets and Languages. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2037– 2050, D… find
  2. Christoph Alt, Aleksandra Gabryszak, and Leonhard Hennig. 2020. Probing Linguistic Features of Sentence-Level Representations in Relation Extraction. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 1534–1545, Online. Association for Computational Lin… find
  3. David Arps, Younes Samih, Laura Kallmeyer, and Hassan Sajjad. 2022. Probing for Constituency Structure in Neural Language Models. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 6738–6757, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics. find
  4. Carlos Aspillaga, Marcelo Mendoza, and Alvaro Soto. 2021. Inspecting the concept knowledge graph encoded by modern language models. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 2984–3000, Online. Association for Computational Linguistics. find
  5. Giosuè Baggio. 2021. Compositionality in a parallel architecture for language processing. Cognitive Science, 45(5):e12949. find
  6. Marco Baroni and Roberto Zamparelli. 2010. Nouns are vectors, adjectives are matrices: Representing adjective-noun constructions in semantic space. In Proceedings of the 2010 conference on empirical methods in natural language processing, pages 1183– 1193. find our card
  7. Yonatan Belinkov. 2022. Probing Classifiers: Promises, Shortcomings, and Advances. Computational Linguistics, 48(1):207–219. find our card
  8. Gemma Boleda. 2020. Distributional Semantics and Linguistic Theory. Annual Review of Linguistics, 6(1):213–234. ArXiv:1905.01896 [cs]. — [arXiv:1905.01896](https://arxiv.org/abs/1905.01896) find
  9. Tommi Buder-Gröndahl. 2023. The ambiguity of bertology: what do large language models represent? Synthese, 203(1):15. find
  10. Tommi Buder-Gröndahl. 2024. What does parameter-free probing really uncover? In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 327–336, Bangkok, Thailand. Association for Computational Linguistics. find
  11. Tyler A Chang and Benjamin K Bergen. 2024. Language model behavior: A comprehensive survey. Computational Linguistics, 50(1):293–350. find
  12. Zeming Chen and Qiyue Gao. 2022. Probing Linguistic Information for Logical Inference in Pre-trained Language Models. Proceedings of the AAAI Conference on Artificial Intelligence, 36(10):10509–10517. find
  13. Rochelle Choenni and Ekaterina Shutova. 2022. Investigating Language Relationships in Multilingual Sentence Encoders Through the Lens of Linguistic Typology. Computational Linguistics, 48(3):635– 672. find
  14. Gabriella Chronis, Kyle Mahowald, and Katrin Erk. 2023. A method for studying semantic construal in grammatical constructions with interpretable contextual embedding spaces. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 242–… find
  15. Alexis Conneau, German Kruszewski, Guillaume Lample, Loïc Barrault, and Marco Baroni. 2018. What you can cram into a single $&!\#* vector: Probing sentence embeddings for linguistic properties. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long… find our card
  16. Alice Coucke, Alaa Saade, Adrien Ball, Théodore Bluche, Alexandre Caulier, David Leroy, Clément Doumouro, Thibault Gisselbrecht, Francesco Caltagirone, Thibaut Lavril, and 1 others. 2018. Snips voice platform: an embedded spoken language understanding system for private-by-design voice interfaces. a… find our card
  17. Hoagy Cunningham, Aidan Ewart, Logan Riggs, Robert Huben, and Lee Sharkey. 2023. Sparse autoencoders find highly interpretable features in language models. arXiv preprint arXiv:2309.08600. find
  18. Verna Dankers, Christopher Lucas, and Ivan Titov. 2022. Can transformer be too compositional? analysing idiom processing in neural machine translation. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 3608–3626, Dublin, Ireland… find our card
  19. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies,… find
  20. Irene Heim and Angelika Kratzer. 1998. Semantics in Generative Grammar. Blackwell, Malden, MA. find
  21. David R Dowty. 1979. Word meaning and montague grammar. Studies in Linguistics and Philosophy. find
  22. Frances Egan. 2018. Function-theoretic explanation and the search for neural mechanisms. In Explanation and Integration in Mind and Brain Science, pages 145–163. Oxford University Press. find
  23. John Hewitt and Percy Liang. 2019. Designing and interpreting probes with control tasks. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 2733–2743, Hong Kong, Chi… find
  24. Yanai Elazar, Shauli Ravfogel, Alon Jacovi, and Yoav Goldberg. 2021. Amnesic Probing: Behavioral Explanation with Amnesic Counterfactuals. Transactions of the Association for Computational Linguistics, 9:160–175. find our card
  25. Dieuwke Hupkes, Sara Veldhoen, and Willem Zuidema. 2018. Visualisation and ’Diagnostic Classifiers’ Reveal How Recurrent and Recursive Neural Networks Process Hierarchical Structure. Journal of Artificial Intelligence Research, 61:907–926. find
  26. David Embick and David Poeppel. 2015. Towards a computational (ist) neurobiology of language: correlational, integrated and explanatory neurolinguistics. Language, cognition and neuroscience, 30(4):357– 366. find
  27. Ganesh Jawahar, Benoît Sagot, and Djamé Seddah. 2019. What Does BERT Learn about the Structure of Language? In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 3651–3657, Florence, Italy. Association for Computational Linguistics. find our card
  28. Mihail Eric, Rahul Goel, Shachi Paul, Adarsh Kumar, Abhishek Sethi, Peter Ku, Anuj Kumar Goyal, Sanchit Agarwal, Shuyang Gao, and Dilek Hakkani-Tur. 2019. Multiwoz 2.1: A consolidated multi-domain dialogue dataset with state corrections and state tracking baselines. arXiv preprint arXiv:1907.01669. find
  29. Christiane Fellbaum. 1998. WordNet: An electronic lexical database. MIT press. find
  30. Jerry A Fodor and Zenon W Pylyshyn. 1988. Connectionism and cognitive architecture: A critical analysis. Cognition, 28(1-2):3–71. find
  31. Daniel Furrer, Marc van Zee, Nathan Scales, and Nathanael Schärli. 2021. Compositional Generalization in Semantic Parsing: Pre-training vs. Specialized Architectures. arXiv preprint. ArXiv:2007.08970 [cs]. find
  32. Atticus Geiger, Duligur Ibeling, Amir Zur, Maheep Chaudhary, Sonakshi Chauhan, Jing Huang, Aryaman Arora, Zhengxuan Wu, Noah Goodman, Christopher Potts, and 1 others. 2025. Causal abstraction: A theoretical foundation for mechanistic interpretability. Journal of Machine Learning Research, 26(83):1–6… find
  33. Adele E Goldberg. 2015. Compositionality. In The Routledge handbook of semantics, pages 419–433. Routledge. find
  34. Adele E Goldberg. 2024. Usage-based constructionist approaches and large language models. Constructions and Frames, 16(2):220–254. find
  35. Robert F Hadley. 1994. Systematicity in connectionist language learning. Mind & Language, 9(3):247–272. find
  36. Pengcheng He, Xiaodong Liu, Jianfeng Gao, and Weizhu Chen. 2021. Deberta: Decoding-enhanced bert with disentangled attention. In International Conference on Learning Representations. find our card
  37. Tianjie Ju, Weiwei Sun, Wei Du, Xinwei Yuan, Zhaochun Ren, and Gongshen Liu. 2024. How large language models encode context knowledge? a layer-wise probing study. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 20… find
  38. Jaap Jumelet, Milica Denic, Jakub Szymanik, Dieuwke Hupkes, and Shane Steinert-Threlkeld. 2021. Language models use monotonicity to assess NPI licensing. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 4958– 4969, Online. Association for Computational Linguistics… find
  39. Saffron Kendrick, Mark Ormerod, Hui Wang, and Barry Devereux. 2025. Investigating noun-noun compound relation representations in autoregressive large language models. In Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics, pages 253–263, Albuquerque, New Mexico, USA. Asso… find
  40. Daniel Keysers, Nathanael Schärli, Nathan Scales, Hylke Buisman, Daniel Furrer, Sergii Kashubin, Nikola Momchev, Danila Sinopalnikov, Lukasz Stafiniak, Tibor Tihon, Dmitry Tsarkov, Xiao Wang, Marc van Zee, and Olivier Bousquet. 2020. Measuring compositional generalization: A comprehensive method on… find
  41. Najoung Kim and Tal Linzen. 2020. COGS: A compositional generalization challenge based on semantic interpretation. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 9087–9105, Online. Association for Computational Linguistics. find
  42. Filip Klubička, Vasudevan Nedumpozhimana, and John Kelleher. 2023. Idioms, Probing and Dangerous Things: Towards Structural Probing for Idiomaticity in Vector Space. In Proceedings of the 19th Workshop on Multiword Expressions (MWE 2023), pages 45–57, Dubrovnik, Croatia. Association for Computation… find
  43. John W Krakauer, Asif A Ghazanfar, Alex Gomez-Marin, Malcolm A MacIver, and David Poeppel. 2017. Neuroscience needs behavior: correcting a reductionist bias. Neuron, 93(3):480–490. find
  44. Ilia Kuznetsov and Iryna Gurevych. 2020. A matter of framing: The impact of linguistic formalism on probing results. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 171–182, Online. Association for Computational Linguistics. find
  45. Brenden Lake and Marco Baroni. 2018. Generalization without systematicity: On the compositional skills of sequence-to-sequence recurrent networks. In International conference on machine learning, pages 2873–2882. PMLR. find
  46. Angeliki Lazaridou, Marco Marelli, Roberto Zamparelli, and Marco Baroni. 2013. Compositional-ly derived representations of morphologically complex words in distributional semantics. In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pa… find
  47. Alessandro Lenci. 2011. Composing and updating verb argument expectations: A distributional semantic model. In Proceedings of the 2nd Workshop on Cognitive Modeling and Computational Linguistics, pages 58–66, Portland, Oregon, USA. Association for Computational Linguistics. find
  48. Alessandro Lenci, Magnus Sahlgren, Patrick Jeuniaux, Amaru Cuba Gyllensten, and Martina Miliani. 2022. A comparative evaluation and analysis of three generations of distributional semantic models. Language resources and evaluation, 56(4):1269–1313. find
  49. Hector J Levesque, Ernest Davis, and Leora Morgenstern. 2012. The winograd schema challenge. KR, 2012:13th. find
  50. Bai Li, Zining Zhu, Guillaume Thomas, Frank Rudzicz, and Yang Xu. 2022. Neural reality of argument structure constructions. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 7410–7423, Dublin, Ireland. Association for Computatio… find
  51. Belinda Z. Li, Maxwell Nye, and Jacob Andreas. 2021. Implicit Representations of Meaning in Neural Language Models. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Pa… find
  52. Ruiqi Li, Xiang Zhao, and Marie-Francine Moens. 2023. A Brief Overview of Universal Sentence Representation Methods: A Linguistic View. ACM Computing Surveys, 55(3):1–42. find
  53. Ruixi Lin and Hwee Tou Ng. 2022. Does BERT Know that the IS-A Relation Is Transitive? In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 94–99, Dublin, Ireland. Association for Computational Linguistics. find
  54. Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692. find
  55. Qing Lyu, Zheng Hua, Daoxin Li, Li Zhang, Marianna Apidianaki, and Chris Callison-Burch. 2022. Is “My Favorite New Movie” My Favorite Movie? Probing the Understanding of Recursive Noun Phrases. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational L… find
  56. David Marr. 1982. Vision : a computational investigation into the human representation and processing of visual information. W.H. Freeman. find
  57. R. Thomas McCoy, Ellie Pavlick, and Tal Linzen. 2019. Right for the wrong reasons: Diagnosing syntactic heuristics in natural language inference. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 3428–3448, Florence, Italy. Association for Computationa… find our card
  58. Jack Merullo, Carsten Eickhoff, and Ellie Pavlick. 2024. Language models implement simple Word2Vec-style vector arithmetic. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages… find
  59. Eleni Metheniti, Tim Van De Cruys, and Nabil Hathout. 2022. About time: Do transformers learn temporal verbal aspect? In Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics, pages 88–101, Dublin, Ireland. Association for Computational Linguistics. find
  60. Alessio Miaschi, Dominique Brunato, Felice Dell’Orletta, and Giulia Venturi. 2020. Linguistic Profiling of a Neural Language Model. In Proceedings of the 28th International Conference on Computational Linguistics, pages 745–756, Barcelona, Spain (Online). International Committee on Computational Lin… find
  61. Alessio Miaschi and Felice Dell’Orletta. 2020. Contextual and Non-Contextual Word Embeddings: an in-depth Linguistic Investigation. In Proceedings of the 5th Workshop on Representation Learning for NLP, pages 110–119, Online. Association for Computational Linguistics. find
  62. Giulia Rambelli, Emmanuele Chersoni, Philippe Blache, Chu-Ren Huang, and Alessandro Lenci. 2019. Distributional semantics meets construction grammar. towards a unified usage-based model of grammar and meaning. In First international workshop on designing meaning representations (DMR 2019). find
  63. Julian Michael, Jan A. Botha, and Ian Tenney. 2020. Asking without telling: Exploring latent ontologies in contextual representations. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 6792–6812, Online. Association for Computational Linguistics… find
  64. Pegah Ramezani, Achim Schilling, and Patrick Krauss. 2025. Analysis of argument structure constructions in the large language model bert. Frontiers in Artificial Intelligence, 8:1477246. find
  65. Vladislav Mikhailov, Oleg Serikov, and Ekaterina Artemova. 2021. Morph Call: Probing Morphosyntactic Content of Multilingual Transformers. In Proceedings of the Third Workshop on Computational Typology and Multilingual NLP, pages 97–121, Online. Association for Computational Linguistics. find
  66. Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg S Corrado, and Jeff Dean. 2013. Distributed representations of words and phrases and their compositionality. Advances in neural information processing systems, 26. find
  67. Melanie Mitchell and David C. Krakauer. 2023. The debate over understanding in AI’s large language models. Proceedings of the National Academy of Sciences, 120(13):e2215907120. find
  68. Ludovica Pannitto and Aurélie Herbelot. 2023. CALaMo: a constructionist assessment of language models. In Proceedings of the First International Workshop on Construction Grammars and NLP (CxGs+NLP, GURT/SyntaxFest 2023), pages 21–30, Washington, D.C. Association for Computational Linguistics. find
  69. Barbara Partee and 1 others. 1995. Lexical semantics and compositionality. An invitation to cognitive science: Language, 1:311–360. find
  70. Tiago Pimentel, Naomi Saphra, Adina Williams, and Ryan Cotterell. 2020a. Pareto probing: Trading off accuracy for complexity. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 3138–3153, Online. Association for Computational Linguistics. find
  71. Tiago Pimentel, Josef Valvoda, Rowan Hall Maudslay, Ran Zmigrod, Adina Williams, and Ryan Cotterell. 2020b. Information-Theoretic Probing for Linguistic Structure. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 4609–4622, Online. Association for Com… find our card
  72. David Poeppel and David Embick. 2017. Defining the relation between linguistics and neuroscience. In Twenty-first century psycholinguistics, pages 103– 118. Routledge. find
  73. James Pustejovsky. 1998. The generative lexicon. MIT press. find
  74. Abhilasha Ravichander, Yonatan Belinkov, and Eduard Hovy. 2021. Probing the Probing Paradigm: Does Probing Accuracy Entail Task Relevance? In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 3363–3377, Online. Association… find
  75. Samuel Ryb, Mario Giulianelli, Arabella Sinclair, and Raquel Fernández. 2022. AnaLog: Testing Analytical and Deductive Logic Learnability in Language Models. In Proceedings of the 11th Joint Conference on Lexical and Computational Semantics, pages 55–68, Seattle, Washington. Association for Computat… find
  76. Abdelrhman Saleh, Tovly Deutsch, Stephen Casper, Yonatan Belinkov, and Stuart Shieber. 2020. Probing Neural Dialog Models for Conversational Understanding. In Proceedings of the 2nd Workshop on Natural Language Processing for Conversational AI, pages 132–143, Online. Association for Computational Li… find
  77. Nina Schneidermann, Daniel Hershcovich, and Bolette Pedersen. 2023. Probing for Hyperbole in Pre-Trained Language Models. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop), pages 200–211, Toronto, Canada. Association for… find
  78. Wesley Scivetti and Nathan Schneider. 2025. Construction identification and disambiguation using BERT: A case study of NPN. In Proceedings of the 29th Conference on Computational Natural Language Learning, pages 365–376, Vienna, Austria. Association for Computational Linguistics. find
  79. John R Searle and Daniel Vanderveken. 1985. Foundations of illocutionary logic. CUP Archive. find
  80. Giulio Starace, Konstantinos Papakostas, Rochelle Choenni, Apostolos Panagiotopoulos, Matteo Rosati, Alina Leidinger, and Ekaterina Shutova. 2023. Probing LLMs for joint encoding of linguistic categories. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 7158–7179, Sing… find
  81. Alfred Tarski. 1944. The semantic conception of truth: and the foundations of semantics. Philosophy and phenomenological research, 4(3):341–376. find
  82. Harish Tayyar Madabushi, Laurence Romain, Dagmar Divjak, and Petar Milin. 2020. CxGBERT: BERT meets construction grammar. In Proceedings of the 28th International Conference on Computational Linguistics, pages 4020–4032, Barcelona, Spain (Online). International Committee on Computational Linguistics… find
  83. Kelly Zhang and Samuel Bowman. 2018. Language modeling teaches you more than translation does: Lessons learned through auxiliary syntactic task analysis. In Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, pages 359–361, Brussels, Belgium. Assoc… find
  84. Ian Tenney, Patrick Xia, Berlin Chen, Alex Wang, Adam Poliak, R Thomas McCoy, Najoung Kim, Benjamin Van Durme, Samuel R. Bowman, Dipanjan Das, and Ellie Pavlick. 2019. What do you learn from context? Probing for sentence structure in contextualized word representations. arXiv preprint. Version Numbe… find our card
  85. Mengjie Zhao, Philipp Dufter, Yadollah Yaghoobzadeh, and Hinrich Schütze. 2020. Quantifying the Contextualization of Word Representations with Semantic Class Probing. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 1219–1234, Online. Association for Computational Ling… find
  86. Aaron Traylor, Roman Feiman, and Ellie Pavlick. 2021. AND does not mean OR: Using Formal Languages to Study Language Models’ Representations. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Pro… find
  87. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems, 30. find
  88. Martina G. Vilas, Federico Adolfi, David Poeppel, and Gemma Roig. 2024. Position: An inner interpretability framework for AI inspired by lessons from cognitive neuroscience. In Proceedings of the 41st International Conference on Machine Learning, volume 235 of Proceedings of Machine Learning Researc… find
  89. Elena Voita and Ivan Titov. 2020. Information-Theoretic Probing with Minimum Description Length. arXiv preprint. ArXiv:2003.12298 [cs]. find our card
  90. Andreas Waldis, Yotam Perlitz, Leshem Choshen, Yufang Hou, and Iryna Gurevych. 2024. Holmes a benchmark to assess the linguistic competence of language models. Transactions of the Association for Computational Linguistics, 12:1616–1647. find
  91. Jonas Wallat, Fabian Beringer, Abhijit Anand, and Avishek Anand. 2023. Probing BERT for Ranking Abilities. In Advances in Information Retrieval, pages 255–273, Cham. Springer Nature Switzerland. find
  92. Barry Wang, Xinya Du, and Claire Cardie. 2023. Probing Representations for Document-level Event Extraction. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 12675– 12683, Singapore. Association for Computational Linguistics. find
  93. Ralph Weischedel, Martha Palmer, Mitchell Marcus, Eduard Hovy, Sameer Pradhan, Lance Ramshaw, Nianwen Xue, Ann Taylor, Jeff Kaufman, Michelle Franchini, and 1 others. 2013. Ontonotes release 5.0 ldc2013t19. Linguistic Data Consortium, Philadelphia, PA, 23(170):20. find

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/papers/marro-2026-compositional-meaning-representations-llms-critical/