6 accepted papers
Open-weight AI systems offer unique benefits, including enhanced transparency, open research, and decentralized access. However, they are vulnerable to tampering attacks which can efficiently elicit harmful behaviors by modifying weights or activations. Currently, there is not yet a robust science o…
Large language models are increasingly becoming a cornerstone technology in artificial intelligence, the sciences, and society as a whole, yet the optimal strategies for dataset composition and filtering remain largely elusive. Many of the top-performing models lack transparency in their dataset cur…
Memorization, or the tendency of large language models (LLMs) to output entire sequences from their training data verbatim, is a key concern for deploying language models. In particular, it is vital to minimize a model's memorization of sensitive datapoints such as those containing personal identifi…
How do large language models (LLMs) develop and evolve over the course of training? How do these patterns change as models scale? To answer these questions, we introduce *Pythia*, a suite of 16 LLMs all trained on public data seen in the exact same order and ranging in size from 70M to 12B parameter…
Transformers have revolutionized almost all natural language processing (NLP) tasks but suffer from memory and computational complexity that scales quadratically with sequence length. In contrast, recurrent neural networks (RNNs) exhibit linear scaling in memory and computational requirements but st…
Reinforcement learning from human feedback (\textbf{RLHF}) utilizes human feedback to better align large language models with human preferences via online optimization against a learned reward model. Current RLHF paradigms rely on Proximal Policy Optimization (\textbf{PPO}), which quickly becomes a…