Large Language Models as Attribution Regularizers for Efficient Model Training
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913959480655872 |
|---|---|
| author | Vukadin, Davor Šilić, Marin Delač, Goran |
| author_facet | Vukadin, Davor Šilić, Marin Delač, Goran |
| contents | Large Language Models (LLMs) have demonstrated remarkable performance across diverse domains. However, effectively leveraging their vast knowledge for training smaller downstream models remains an open challenge, especially in domains like tabular data learning, where simpler models are often preferred due to interpretability and efficiency.
In this paper, we introduce a novel yet straightforward method for incorporating LLM-generated global task feature attributions into the training process of smaller networks. Specifically, we propose an attribution-matching regularization term that aligns the training dynamics of the smaller model with the insights provided by the LLM. By doing so, our approach yields superior performance in few-shot learning scenarios. Notably, our method requires only black-box API access to the LLM, making it easy to integrate into existing training pipelines with minimal computational overhead.
Furthermore, we demonstrate how this method can be used to address common issues in real-world datasets, such as skewness and bias. By integrating high-level knowledge from LLMs, our approach improves generalization, even when training data is limited or imbalanced. We validate its effectiveness through extensive experiments across multiple tasks, demonstrating improved learning efficiency and model robustness. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_20268 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Large Language Models as Attribution Regularizers for Efficient Model Training Vukadin, Davor Šilić, Marin Delač, Goran Machine Learning Artificial Intelligence I.2.6 Large Language Models (LLMs) have demonstrated remarkable performance across diverse domains. However, effectively leveraging their vast knowledge for training smaller downstream models remains an open challenge, especially in domains like tabular data learning, where simpler models are often preferred due to interpretability and efficiency. In this paper, we introduce a novel yet straightforward method for incorporating LLM-generated global task feature attributions into the training process of smaller networks. Specifically, we propose an attribution-matching regularization term that aligns the training dynamics of the smaller model with the insights provided by the LLM. By doing so, our approach yields superior performance in few-shot learning scenarios. Notably, our method requires only black-box API access to the LLM, making it easy to integrate into existing training pipelines with minimal computational overhead. Furthermore, we demonstrate how this method can be used to address common issues in real-world datasets, such as skewness and bias. By integrating high-level knowledge from LLMs, our approach improves generalization, even when training data is limited or imbalanced. We validate its effectiveness through extensive experiments across multiple tasks, demonstrating improved learning efficiency and model robustness. |
| title | Large Language Models as Attribution Regularizers for Efficient Model Training |
| topic | Machine Learning Artificial Intelligence I.2.6 |
| url | https://arxiv.org/abs/2502.20268 |