On the Importance of Data Size in Probing Fine-tuned Models
This addresses a gap in probing studies for researchers in NLP, but it is incremental as it focuses on a specific factor in fine-tuning.
The paper tackles the problem of understanding how fine-tuning data size affects probing performance, showing that the amount of encoded linguistic knowledge depends on the number of fine-tuning samples, with larger data mainly impacting higher layers and recoverability of changes.
Several studies have investigated the reasons behind the effectiveness of fine-tuning, usually through the lens of probing. However, these studies often neglect the role of the size of the dataset on which the model is fine-tuned. In this paper, we highlight the importance of this factor and its undeniable role in probing performance. We show that the extent of encoded linguistic knowledge depends on the number of fine-tuning samples. The analysis also reveals that larger training data mainly affects higher layers, and that the extent of this change is a factor of the number of iterations updating the model during fine-tuning rather than the diversity of the training samples. Finally, we show through a set of experiments that fine-tuning data size affects the recoverability of the changes made to the model's linguistic knowledge.