mlsanityData to 7 Oct 2026

Can We Use Probing to Better Understand Fine-tuning and Knowledge Distillation of the BERT NLU?

arXiv 2301.11688 ↗First posted 27 Jan 2023cs.CL cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

In this article, we use probing to investigate phenomena that occur during fine-tuning and knowledge distillation of a BERT-based natural language understanding (NLU) model. Our ultimate purpose was to use probing to better understand practical production problems and consequently to build better NLU models. We designed experiments to see how fine-tuning changes the linguistic capabilities of BERT, what the optimal size of the fine-tuning dataset is, and what amount of information is contained in a distilled NLU based on a tiny Transformer. The results of the experiments show that the probing paradigm in its current form is not well suited to answer such questions. Structural, Edge and Conditional probes do not take into account how easy it is to decode probed information. Consequently, we conclude that quantification of information decodability is critical for many practical applications of the probing paradigm.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 27 of its 32 references that are in the map. First posted on arXiv 27 Jan 2023.

Builds on

27 of 32 references.

References · 27

  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. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  4. 2019PIQA: Reasoning about Physical Commonsense in Natural Languagecited by 2,818
  5. 2019What Does BERT Look At? An Analysis of BERT's Attentioncited by 994
  6. 2019What do you learn from context? Probing for sentence structure in contextualized word representationscited by 436
  7. 2019Linguistic Knowledge and Transferability of Contextual Representationscited by 382
  8. 2019On Mutual Information Maximization for Representation Learningcited by 315
  9. 2020Universal Dependencies v2: An Evergrowing Multilingual Treebank Collectioncited by 269
  10. 2020Information-Theoretic Probing for Linguistic Structurecited by 204
  11. 2019BERT for Joint Intent Classification and Slot Fillingcited by 195
  12. 2020A Systematic Assessment of Syntactic Generalization in Neural Language Modelscited by 163
15 more
  1. 2020A Theory of Usable Information Under Computational Constraintscited by 153
  2. 2020What Happens To BERT Embeddings During Fine-tuning?cited by 113
  3. 2020When Do You Need Billions of Words of Pretraining Data?cited by 104
  4. 2021Conditional probing: measuring usable information beyond a baselinecited by 61
  5. 2017Machine learning for neural decodingcited by 45
  6. 2020On the Interplay Between Fine-tuning and Sentence-level Probing for Linguistic Knowledge in Pre-trained Transformerscited by 39
  7. 2021How transfer learning impacts linguistic knowledge in deep NLP models?cited by 32
  8. 2018Interpreting Encoding and Decoding Modelscited by 21
  9. 2021How much pretraining data do language models need to learn syntax?cited by 21
  10. 2021Probing artificial neural networks: insights from neurosciencecited by 17
  11. 2020Mimic and Conquer: Heterogeneous Tree Structure Distillation for Syntactic NLPcited by 15
  12. 2022Predicting Fine-Tuning Performance with Probingcited by 13
  13. 2019Scalable Syntax-Aware Language Models Using Knowledge Distillationcited by 8
  14. 2021The Rediscovery Hypothesis: Language Models Need to Meet Linguisticscited by 7
  15. 2020Syntax Representation in Word Embeddings and Neural Networks -- A Surveycited by 5

Built on by

Cited by year

Citing papers per year: 2024: 1.

1 paper.

  1. 2024Non-Linear Inference Time Intervention: Improving LLM Truthfulnesscited by 9