6 papers
When Should We Introduce Safety Interventions During Pretraining?
Dylan Sam, Sachin Goyal, Pratyush Maini +2
Prior work has shown that safety interventions applied during pretraining, such as removing and rephrasing harmful content, can substantially improve the robustness of the resultin…
Mode-Conditioning Unlocks Superior Test-Time Scaling
Chen Henry Wu, Sachin Goyal, Aditi Raghunathan
Parallel sampling promises substantial gains in test-time scaling, but its effectiveness is sharply limited by diversity collapse, where models concentrate on a few modes and repea…
Safety Pretraining: Toward the Next Generation of Safe AI
Pratyush Maini, Sachin Goyal, Dylan Sam +7
As large language models (LLMs) are increasingly deployed in high-stakes settings, the risk of generating harmful or toxic content remains a central challenge. Post-hoc alignment m…
Inference Optimal VLMs Need Fewer Visual Tokens and More Parameters
Kevin Y. Li, Sachin Goyal, Joao D. Semedo +1
Vision Language Models (VLMs) have demonstrated strong capabilities across various visual understanding and reasoning tasks, driven by incorporating image representations into the…
Context-Parametric Inversion: Why Instruction Finetuning Can Worsen Context Reliance
Sachin Goyal, Christina Baek, J. Zico Kolter +1
A standard practice when using large language models is for users to supplement their instruction with an input context containing new information for the model to process. However…
Overtrained Language Models Are Harder to Fine-Tune
Jacob Mitchell Springer, Sachin Goyal, Kaiyue Wen +5
Large language models are pre-trained on ever-growing token budgets under the assumption that better pre-training performance translates to improved downstream models. In this work…