Effects of Scale on Language Model Robustness

• URL: http://arxiv.org/abs/2407.18213v3
• Date: Thu, 24 Oct 2024 04:40:06 GMT
• Title: Effects of Scale on Language Model Robustness
• Authors: Nikolaus Howe, Ian McKenzie, Oskar Hollinsworth, Michał Zajac, Tom Tseng, Aaron Tucker, Pierre-Luc Bacon, Adam Gleave,
• Abstract summary: We show that adversarially trained larger models generalize faster and better to modified attacks not seen during training when compared with smaller models. We also analyze the offense/defense balance of increasing compute, finding parity in some settings and an advantage for offense in others.
• Score: 7.725206196110384
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Language models exhibit scaling laws, whereby increasing model and dataset size yields predictable decreases in negative log likelihood, unlocking a dazzling array of capabilities. This phenomenon spurs many companies to train ever larger models in pursuit of ever improved performance. Yet, these models are vulnerable to adversarial inputs such as ``jailbreaks'' and prompt injections that induce models to perform undesired behaviors, posing a growing risk as models become more capable. Prior work indicates that computer vision models become more robust with model and data scaling, raising the question: does language model robustness also improve with scale? We study this question empirically in the classification setting, finding that without explicit defense training, larger models tend to be modestly more robust on most tasks, though the effect is not reliable. Even with the advantage conferred by scale, undefended models remain easy to attack in absolute terms, and we thus turn our attention to explicitly training models for adversarial robustness, which we show to be a much more compute-efficient defense than scaling model size alone. In this setting, we also observe that adversarially trained larger models generalize faster and better to modified attacks not seen during training when compared with smaller models. Finally, we analyze the offense/defense balance of increasing compute, finding parity in some settings and an advantage for offense in others, suggesting that adversarial training alone is not sufficient to solve robustness, even at greater model scales.

Related papers

• Scaling Laws for Black box Adversarial Attacks [37.744814957775965]
  Adversarial examples exhibit cross-model transferability, enabling to attack black-box models. Model ensembling is an effective strategy to improve the transferability by attacking multiple surrogate models simultaneously. We show that scaled attacks bring better interpretability in semantics, indicating that the common features of models are captured.
  arXiv  Detail & Related papers  (2024-11-25T08:14:37Z)
• A Hitchhiker's Guide to Scaling Law Estimation [56.06982415792523]
  Scaling laws predict the loss of a target machine learning model by extrapolating from easier-to-train models with fewer parameters or smaller training sets. We estimate more than 1000 scaling laws, then derive a set of best practices for estimating scaling laws in new model families.
  arXiv  Detail & Related papers  (2024-10-15T17:59:10Z)
• Strong Model Collapse [16.071600606637908]
  We consider a supervised regression setting and establish the existance of a strong form of the model collapse phenomenon. Our results show that even the smallest fraction of synthetic data can lead to model collapse. We investigate whether increasing model size, an approach aligned with current trends in training large language models, exacerbates or mitigates model collapse.
  arXiv  Detail & Related papers  (2024-10-07T08:54:23Z)
• Scalable Ensembling For Mitigating Reward Overoptimisation [24.58937616758007]
  Reinforcement Learning from Human Feedback has enabled significant advancements within language modeling for powerful, instruction-following models. The alignment of these models remains a pressing challenge as the policy tends to overfit the learned proxy" reward model past an inflection point of utility.
  arXiv  Detail & Related papers  (2024-06-03T05:46:53Z)
• Observational Scaling Laws and the Predictability of Language Model Performance [51.2336010244645]
  We propose an observational approach that bypasses model training and instead builds scaling laws from 100 publically available models. We show that several emergent phenomena follow a smooth, sigmoidal behavior and are predictable from small models. We show how to predict the impact of post-training interventions like Chain-of-Thought and Self-Consistency as language model capabilities continue to improve.
  arXiv  Detail & Related papers  (2024-05-17T17:49:44Z)
• Interpretable Computer Vision Models through Adversarial Training: Unveiling the Robustness-Interpretability Connection [0.0]
  Interpretability is as essential as robustness when we deploy the models to the real world. Standard models, compared to robust are more susceptible to adversarial attacks, and their learned representations are less meaningful to humans.
  arXiv  Detail & Related papers  (2023-07-04T13:51:55Z)
• Training Trajectories of Language Models Across Scales [99.38721327771208]
  Scaling up language models has led to unprecedented performance gains. How do language models of different sizes learn during pre-training? Why do larger language models demonstrate more desirable behaviors?
  arXiv  Detail & Related papers  (2022-12-19T19:16:29Z)
• Predicting on the Edge: Identifying Where a Larger Model Does Better [61.793778186198864]
  We show that large models have the largest improvement on examples where the small model is most uncertain. We show that a switcher model which defers examples to a larger model when a small model is uncertain can achieve striking improvements in performance and resource usage.
  arXiv  Detail & Related papers  (2022-02-15T18:53:14Z)
• "What's in the box?!": Deflecting Adversarial Attacks by Randomly Deploying Adversarially-Disjoint Models [71.91835408379602]
  adversarial examples have been long considered a real threat to machine learning models. We propose an alternative deployment-based defense paradigm that goes beyond the traditional white-box and black-box threat models.
  arXiv  Detail & Related papers  (2021-02-09T20:07:13Z)
• Train Large, Then Compress: Rethinking Model Size for Efficient Training and Inference of Transformers [94.43313684188819]
  We study the impact of model size in this setting, focusing on Transformer models for NLP tasks that are limited by compute. We first show that even though smaller Transformer models execute faster per iteration, wider and deeper models converge in significantly fewer steps. This leads to an apparent trade-off between the training efficiency of large Transformer models and the inference efficiency of small Transformer models.
  arXiv  Detail & Related papers  (2020-02-26T21:17:13Z)

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.