Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2512.11912 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917143981850624 |
|---|---|
| author | Peng, Liu Jin, Yaochu |
| author_facet | Peng, Liu Jin, Yaochu |
| contents | A systematic, comparative investigation into the effects of low-quality data reveals a stark spectrum of robustness across modern probabilistic models. We find that autoregressive language models, from token prediction to sequence-to-sequence tasks, are remarkably resilient (for GPT-2, test NLL increases modestly from 2.87 to 3.59 despite 50% token corruption). By contrast, under the same levels of data corruption, class-conditional diffusion models degrade catastrophically (image-label consistency plummets by 56.81% relative to baseline), while classifiers show a moderate impact that diminishes with dataset scale. To explain these discrepancies, we analyze the results through a multi-perspective lens, integrating information theory, PAC learning, and gradient dynamics. These analyses suggest that robustness is heavily influenced by two key principles: the richness of conditioning information, which constrains the learning problem, and the absolute information content of the training data, which allows the signal from correct information to dominate statistical noise. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_11912 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Robustness of Probabilistic Models to Low-Quality Data: A Multi-Perspective Analysis Peng, Liu Jin, Yaochu Artificial Intelligence A systematic, comparative investigation into the effects of low-quality data reveals a stark spectrum of robustness across modern probabilistic models. We find that autoregressive language models, from token prediction to sequence-to-sequence tasks, are remarkably resilient (for GPT-2, test NLL increases modestly from 2.87 to 3.59 despite 50% token corruption). By contrast, under the same levels of data corruption, class-conditional diffusion models degrade catastrophically (image-label consistency plummets by 56.81% relative to baseline), while classifiers show a moderate impact that diminishes with dataset scale. To explain these discrepancies, we analyze the results through a multi-perspective lens, integrating information theory, PAC learning, and gradient dynamics. These analyses suggest that robustness is heavily influenced by two key principles: the richness of conditioning information, which constrains the learning problem, and the absolute information content of the training data, which allows the signal from correct information to dominate statistical noise. |
| title | Robustness of Probabilistic Models to Low-Quality Data: A Multi-Perspective Analysis |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2512.11912 |