Learning Mechanism Underlying NLP Pre-Training and Fine-Tuning

• URL: http://arxiv.org/abs/2509.03407v1
• Date: Wed, 03 Sep 2025 15:32:50 GMT
• Title: Learning Mechanism Underlying NLP Pre-Training and Fine-Tuning
• Authors: Yarden Tzach, Ronit D. Gross, Ella Koresh, Shalom Rosner, Or Shpringer, Tal Halevi, Ido Kanter,
• Abstract summary: Twofold goals are examined; to understand the mechanism underlying successful pre-training and to determine the interplay between the pre-training accuracy and the fine-tuning of classification tasks.<n>Results were based on the BERT-6 architecture pre-trained on the Wikipedia dataset and fine-tuned on the FewRel and DBpedia classification tasks.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Natural language processing (NLP) enables the understanding and generation of meaningful human language, typically using a pre-trained complex architecture on a large dataset to learn the language and next fine-tune its weights to implement a specific task. Twofold goals are examined; to understand the mechanism underlying successful pre-training and to determine the interplay between the pre-training accuracy and the fine-tuning of classification tasks. The following main results were obtained; the accuracy per token (APT) increased with its appearance frequency in the dataset, and its average over all tokens served as an order parameter to quantify pre-training success, which increased along the transformer blocks. Pre-training broke the symmetry among tokens and grouped them into finite, small, strong match token clusters, as inferred from the presented token confusion matrix. This feature was sharpened along the transformer blocks toward the output layer, enhancing its performance considerably compared with that of the embedding layer. Consequently, higher-order language structures were generated by pre-training, even though the learning cost function was directed solely at identifying a single token. These pre-training findings were reflected by the improved fine-tuning accuracy along the transformer blocks. Additionally, the output label prediction confidence was found to be independent of the average input APT, as the input meaning was preserved since the tokens are replaced primarily by strong match tokens. Finally, although pre-training is commonly absent in image classification tasks, its underlying mechanism is similar to that used in fine-tuning NLP classification tasks, hinting at its universality. The results were based on the BERT-6 architecture pre-trained on the Wikipedia dataset and fine-tuned on the FewRel and DBpedia classification tasks.

Related papers

• Revisiting [CLS] and Patch Token Interaction in Vision Transformers [16.71411137558127]
  Vision Transformers have emerged as powerful, scalable and versatile representation learners.<n>We investigate the friction between global and local feature learning under different pre-training strategies.<n>We propose specialized processing paths that selectively disentangle the computational flow of class and patch tokens.
  arXiv  Detail & Related papers  (2026-02-09T13:16:01Z)
• Pooling Attention: Evaluating Pretrained Transformer Embeddings for Deception Classification [0.0]
  BERT embeddings combined with logistic regression outperform neural baselines on LIAR dataset splits.<n>This work positions attention-based token encoders as robust, architecture-centric foundations for veracity tasks.
  arXiv  Detail & Related papers  (2025-11-28T08:32:49Z)
• Tiny language models [0.0]
  This study explores whether tiny language models (TLMs) exhibit the same key qualitative features of large language models (LLMs)<n>We demonstrate that TLMs exhibit a clear performance gap between pre-trained and non-pre-trained models across classification tasks.<n>The classification accuracy achieved by a pre-trained deep TLM architecture can be replicated through a soft committee of multiple, independently pre-trained shallow architectures.
  arXiv  Detail & Related papers  (2025-07-20T08:49:57Z)
• Zero-shot Meta-learning for Tabular Prediction Tasks with Adversarially Pre-trained Transformer [2.1677183904102257]
  We present an Adversarially Pre-trained Transformer (APT) that is able to perform zero-shot meta-learning on tabular prediction tasks without pre-training on any real-world dataset.<n>APT is pre-trained with adversarial synthetic data agents, who deliberately challenge the model with different synthetic datasets.<n>We show that our framework matches state-of-the-art performance on small classification tasks without filtering on dataset characteristics.
  arXiv  Detail & Related papers  (2025-02-06T23:58:11Z)
• Co-training for Low Resource Scientific Natural Language Inference [65.37685198688538]
  We propose a novel co-training method that assigns weights based on the training dynamics of the classifiers to the distantly supervised labels. By assigning importance weights instead of filtering out examples based on an arbitrary threshold on the predicted confidence, we maximize the usage of automatically labeled data. The proposed method obtains an improvement of 1.5% in Macro F1 over the distant supervision baseline, and substantial improvements over several other strong SSL baselines.
  arXiv  Detail & Related papers  (2024-06-20T18:35:47Z)
• Simple-Sampling and Hard-Mixup with Prototypes to Rebalance Contrastive Learning for Text Classification [11.072083437769093]
  We propose a novel model named SharpReCL for imbalanced text classification tasks. Our model even outperforms popular large language models across several datasets.
  arXiv  Detail & Related papers  (2024-05-19T11:33:49Z)
• You Only Need End-to-End Training for Long-Tailed Recognition [8.789819609485225]
  Cross-entropy loss tends to produce highly correlated features on imbalanced data. We propose two novel modules, Block-based Relatively Balanced Batch Sampler (B3RS) and Batch Embedded Training (BET) Experimental results on the long-tailed classification benchmarks, CIFAR-LT and ImageNet-LT, demonstrate the effectiveness of our method.
  arXiv  Detail & Related papers  (2021-12-11T11:44:09Z)
• Pre-training Co-evolutionary Protein Representation via A Pairwise Masked Language Model [93.9943278892735]
  Key problem in protein sequence representation learning is to capture the co-evolutionary information reflected by the inter-residue co-variation in the sequences. We propose a novel method to capture this information directly by pre-training via a dedicated language model, i.e., Pairwise Masked Language Model (PMLM) Our result shows that the proposed method can effectively capture the interresidue correlations and improves the performance of contact prediction by up to 9% compared to the baseline.
  arXiv  Detail & Related papers  (2021-10-29T04:01:32Z)
• Prototypical Classifier for Robust Class-Imbalanced Learning [64.96088324684683]
  We propose textitPrototypical, which does not require fitting additional parameters given the embedding network. Prototypical produces balanced and comparable predictions for all classes even though the training set is class-imbalanced. We test our method on CIFAR-10LT, CIFAR-100LT and Webvision datasets, observing that Prototypical obtains substaintial improvements compared with state of the arts.
  arXiv  Detail & Related papers  (2021-10-22T01:55:01Z)
• On the Transferability of Pre-trained Language Models: A Study from Artificial Datasets [74.11825654535895]
  Pre-training language models (LMs) on large-scale unlabeled text data makes the model much easier to achieve exceptional downstream performance. We study what specific traits in the pre-training data, other than the semantics, make a pre-trained LM superior to their counterparts trained from scratch on downstream tasks.
  arXiv  Detail & Related papers  (2021-09-08T10:39:57Z)
• Training ELECTRA Augmented with Multi-word Selection [53.77046731238381]
  We present a new text encoder pre-training method that improves ELECTRA based on multi-task learning. Specifically, we train the discriminator to simultaneously detect replaced tokens and select original tokens from candidate sets.
  arXiv  Detail & Related papers  (2021-05-31T23:19:00Z)
• MC-BERT: Efficient Language Pre-Training via a Meta Controller [96.68140474547602]
  Large-scale pre-training is computationally expensive. ELECTRA, an early attempt to accelerate pre-training, trains a discriminative model that predicts whether each input token was replaced by a generator. We propose a novel meta-learning framework, MC-BERT, to achieve better efficiency and effectiveness.
  arXiv  Detail & Related papers  (2020-06-10T09:22:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.