Exploring Scaling Trends in LLM Robustness
- URL: http://arxiv.org/abs/2407.18213v1
- Date: Thu, 25 Jul 2024 17:26:41 GMT
- Title: Exploring Scaling Trends in LLM Robustness
- Authors: Nikolhaus Howe, MichaĆ Zajac, Ian McKenzie, Oskar Hollinsworth, Tom Tseng, Pierre-Luc Bacon, Adam Gleave,
- Abstract summary: Language model capabilities predictably improve from scaling a model's size and training data.
These models are vulnerable to adversarial prompts, such as "jailbreaks" that hijack models to perform undesired behaviors.
We find that larger models respond substantially better to adversarial training, but there is little to no benefit from model scale in the absence of explicit defenses.
- Score: 8.057932419561428
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Language model capabilities predictably improve from scaling a model's size and training data. Motivated by this, increasingly large language models have been trained, yielding an array of impressive capabilities. Yet these models are vulnerable to adversarial prompts, such as "jailbreaks" that hijack models to perform undesired behaviors, posing a significant risk of misuse. 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, finding that larger models respond substantially better to adversarial training, but there is little to no benefit from model scale in the absence of explicit defenses.
Related papers
- 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 80 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) - Scaling Vision-Language Models with Sparse Mixture of Experts [128.0882767889029]
We show that mixture-of-experts (MoE) techniques can achieve state-of-the-art performance on a range of benchmarks over dense models of equivalent computational cost.
Our research offers valuable insights into stabilizing the training of MoE models, understanding the impact of MoE on model interpretability, and balancing the trade-offs between compute performance when scaling vision-language models.
arXiv Detail & Related papers (2023-03-13T16:00:31Z) - 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) - Investigating Ensemble Methods for Model Robustness Improvement of Text
Classifiers [66.36045164286854]
We analyze a set of existing bias features and demonstrate there is no single model that works best for all the cases.
By choosing an appropriate bias model, we can obtain a better robustness result than baselines with a more sophisticated model design.
arXiv Detail & Related papers (2022-10-28T17:52:10Z) - Emergent Abilities of Large Language Models [172.08007363384218]
We consider an ability to be emergent if it is not present in smaller models but is present in larger models.
The existence of such emergence implies that additional scaling could further expand the range of capabilities of language models.
arXiv Detail & Related papers (2022-06-15T17:32:01Z) - What Language Model Architecture and Pretraining Objective Work Best for
Zero-Shot Generalization? [50.84738303888189]
We present a large-scale evaluation of modeling choices and their impact on zero-shot generalization.
We train models with over 5 billion parameters for more than 170 billion tokens.
We find that pretrained causal decoder models can be efficiently adapted into non-causal decoder models.
arXiv Detail & Related papers (2022-04-12T14:19:49Z)
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.