# On the Interplay Between Fine-tuning and Sentence-level Probing for Linguistic Knowledge in Pre-trained Transformers

arXiv: https://arxiv.org/abs/2010.02616 · HTML: https://mlsanity.com/paper/2010.02616/

## Key facts

- Cited by 39 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Oct 2020.

## Built on by (most cited first, 30 of 39)

- [Probing Pre-Trained Language Models for Cross-Cultural Differences in Values](https://mlsanity.com/paper/2203.13722/) (2022)
- [AMMUS : A Survey of Transformer-based Pretrained Models in Natural Language Processing](https://mlsanity.com/paper/2108.05542/) (2021)
- [Language Model Behavior: A Comprehensive Survey](https://mlsanity.com/paper/2303.11504/) (2023)
- [A Closer Look at How Fine-tuning Changes BERT](https://mlsanity.com/paper/2106.14282/) (2021)
- [Estimating Knowledge in Large Language Models Without Generating a Single Token](https://mlsanity.com/paper/2406.12673/) (2024)
- [How transfer learning impacts linguistic knowledge in deep NLP models?](https://mlsanity.com/paper/2105.15179/) (2021)
- [Training language models to summarize narratives improves brain alignment](https://mlsanity.com/paper/2212.10898/) (2022)
- [Holmes: A Benchmark to Assess the Linguistic Competence of Language Models](https://mlsanity.com/paper/2404.18923/) (2024)
- [How Does Fine-tuning Affect the Geometry of Embedding Space: A Case Study on Isotropy](https://mlsanity.com/paper/2109.04740/) (2021)
- [Where to start? Analyzing the potential value of intermediate models](https://mlsanity.com/paper/2211.00107/) (2022)
- [Evaluation of RAG Metrics for Question Answering in the Telecom Domain](https://mlsanity.com/paper/2407.12873/) (2024)
- [On the Transformation of Latent Space in Fine-Tuned NLP Models](https://mlsanity.com/paper/2210.12696/) (2022)
- [Towards Tracing Trustworthiness Dynamics: Revisiting Pre-training Period of Large Language Models](https://mlsanity.com/paper/2402.19465/) (2024)
- [Not All Models Localize Linguistic Knowledge in the Same Place: A Layer-wise Probing on BERToids' Representations](https://mlsanity.com/paper/2109.05958/) (2021)
- [Vision-Language Model Fine-Tuning via Simple Parameter-Efficient Modification](https://mlsanity.com/paper/2409.16718/) (2024)
- [Predicting Fine-Tuning Performance with Probing](https://mlsanity.com/paper/2210.07352/) (2022)
- [Hidden State Variability of Pretrained Language Models Can Guide Computation Reduction for Transfer Learning](https://mlsanity.com/paper/2210.10041/) (2022)
- [On the Importance of Data Size in Probing Fine-tuned Models](https://mlsanity.com/paper/2203.09627/) (2022)
- [Vision-Language Integration in Multimodal Video Transformers (Partially) Aligns with the Brain](https://mlsanity.com/paper/2311.07766/) (2023)
- [Evidence > Intuition: Transferability Estimation for Encoder Selection](https://mlsanity.com/paper/2210.11255/) (2022)
- [On the Interplay Between Fine-tuning and Composition in Transformers](https://mlsanity.com/paper/2105.14668/) (2021)
- [Dive into the Chasm: Probing the Gap between In- and Cross-Topic Generalization](https://mlsanity.com/paper/2402.01375/) (2024)
- [Transformers with Learnable Activation Functions](https://mlsanity.com/paper/2208.14111/) (2022)
- [Aligned Probing: Relating Toxic Behavior and Model Internals](https://mlsanity.com/paper/2503.13390/) (2025)
- [Life after BERT: What do Other Muppets Understand about Language?](https://mlsanity.com/paper/2205.10696/) (2022)
- [Interpretability in Activation Space Analysis of Transformers: A Focused Survey](https://mlsanity.com/paper/2302.09304/) (2023)
- [Topic Aware Probing: From Sentence Length Prediction to Idiom Identification how reliant are Neural Language Models on Topic?](https://mlsanity.com/paper/2403.02009/) (2024)
- [Train More Parameters But Mind Their Placement: Insights into Language Adaptation with PEFT](https://mlsanity.com/paper/2412.12674/) (2024)
- [Joint Modeling of Entities and Discourse Relations for Coherence Assessment](https://mlsanity.com/paper/2509.04182/) (2025)
- [Sentence Ambiguity, Grammaticality and Complexity Probes](https://mlsanity.com/paper/2210.06928/) (2022)

## Abstract (arXiv)

Fine-tuning pre-trained contextualized embedding models has become an integral part of the NLP pipeline. At the same time, probing has emerged as a way to investigate the linguistic knowledge captured by pre-trained models. Very little is, however, understood about how fine-tuning affects the representations of pre-trained models and thereby the linguistic knowledge they encode. This paper contributes towards closing this gap. We study three different pre-trained models: BERT, RoBERTa, and ALBERT, and investigate through sentence-level probing how fine-tuning affects their representations. We find that for some probing tasks fine-tuning leads to substantial changes in accuracy, possibly suggesting that fine-tuning introduces or even removes linguistic knowledge from a pre-trained model. These changes, however, vary greatly across different models, fine-tuning and probing tasks. Our analysis reveals that while fine-tuning indeed changes the representations of a pre-trained model and these changes are typically larger for higher layers, only in very few cases, fine-tuning has a positive effect on probing accuracy that is larger than just using the pre-trained model with a strong pooling method. Based on our findings, we argue that both positive and negative effects of fine-tuning on probing require a careful interpretation.