mlsanityData to 7 Oct 2026

Probing LLMs for Joint Encoding of Linguistic Categories

arXiv 2310.18696 ↗First posted 28 Oct 2023cs.CL cs.AI cs.LGcited by 9

Not on the map. Why?

Abstract (arXiv)

Large Language Models (LLMs) exhibit impressive performance on a range of NLP tasks, due to the general-purpose linguistic knowledge acquired during pretraining. Existing model interpretability research (Tenney et al., 2019) suggests that a linguistic hierarchy emerges in the LLM layers, with lower layers better suited to solving syntactic tasks and higher layers employed for semantic processing. Yet, little is known about how encodings of different linguistic phenomena interact within the models and to what extent processing of linguistically-related categories relies on the same, shared model representations. In this paper, we propose a framework for testing the joint encoding of linguistic categories in LLMs. Focusing on syntax, we find evidence of joint encoding both at the same (related part-of-speech (POS) classes) and different (POS classes and related syntactic dependency relations) levels of linguistic hierarchy. Our cross-lingual experiments show that the same patterns hold across languages in multilingual LLMs.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 33 of its 49 references that are in the map. First posted on arXiv 28 Oct 2023.

Builds on

33 of 49 references.

References · 33

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  4. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,907
  5. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,898
  6. 2018SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processingcited by 1,973
  7. 2019BERT Rediscovers the Classical NLP Pipelinecited by 1,046
  8. 2019What Does BERT Look At? An Analysis of BERT's Attentioncited by 994
  9. 2020A Primer in BERTology: What we know about how BERT workscited by 807
  10. 2019Designing and Interpreting Probes with Control Taskscited by 608
  11. 2021Datasets: A Community Library for Natural Language Processingcited by 526
  12. 2018What you can cram into a single vector: Probing sentence embeddings for linguistic propertiescited by 452
21 more
  1. 2020Null It Out: Guarding Protected Attributes by Iterative Nullspace Projectioncited by 442
  2. 2019What do you learn from context? Probing for sentence structure in contextualized word representationscited by 436
  3. 2019Linguistic Knowledge and Transferability of Contextual Representationscited by 382
  4. 2019Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Settingcited by 346
  5. 2019What BERT is not: Lessons from a new suite of psycholinguistic diagnostics for language modelscited by 317
  6. 2018Analysis Methods in Neural Language Processing: A Surveycited by 276
  7. 2020Universal Dependencies v2: An Evergrowing Multilingual Treebank Collectioncited by 269
  8. 2016Fine-grained Analysis of Sentence Embeddings Using Auxiliary Prediction Taskscited by 216
  9. 2021Post-hoc Interpretability for Neural NLP: A Surveycited by 155
  10. 2020Continual Lifelong Learning in Natural Language Processing: A Surveycited by 152
  11. 2020Finding Universal Grammatical Relations in Multilingual BERTcited by 108
  12. 2019Do Attention Heads in BERT Track Syntactic Dependencies?cited by 87
  13. 2020On the Language Neutrality of Pre-trained Multilingual Representationscited by 82
  14. 2022Discovering Latent Concepts Learned in BERTcited by 56
  15. 2018A Modulation Module for Multi-task Learning with Applications in Image Retrievalcited by 49
  16. 2020Are Pre-trained Language Models Aware of Phrases? Simple but Strong Baselines for Grammar Inductioncited by 47
  17. 2020What's so special about BERT's layers? A closer look at the NLP pipeline in monolingual and multilingual modelscited by 35
  18. 2018Deep RNNs Encode Soft Hierarchical Syntaxcited by 34
  19. 2019LINSPECTOR: Multilingual Probing Tasks for Word Representationscited by 22
  20. 2021A multilabel approach to morphosyntactic probingcited by 8
  21. 2021Similarity of Sentence Representations in Multilingual LMs: Resolving Conflicting Literature and Case Study of Baltic Languagescited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 4; 2026: 3.

9 papers.

  1. 2024Natural Language Processing RELIES on Linguisticscited by 9
  2. 2026Rethinking LLM-as-a-Judge: Representation-as-a-Judge with Small Language Models via Semantic Capacity Asymmetrycited by 8
  3. 2025Different types of syntactic agreement recruit the same units within large language modelscited by 7
  4. 2024Lens: Rethinking Multilingual Enhancement for Large Language Modelscited by 5
  5. 2025RECALL: REpresentation-aligned Catastrophic-forgetting ALLeviation via Hierarchical Model Mergingcited by 5
  6. 2025Semantic Pivots Enable Cross-Lingual Transfer in Large Language Modelscited by 1
  7. 2026From One-to-One to Many-to-Many: Dynamic Cross-Layer Injection for Deep Vision-Language Fusioncited by 1
  8. 2025R2-CoD: Understanding Text-Graph Complementarity in Relational Reasoning via Knowledge Co-Distillationcited by 0
  9. 2026Grammatical "grandmother neurons" are rare in LLMscited by 0