Search Results for author:
Found 16 papers, 9 papers with code
Is Generator Conditioning Causally Related to GAN Performance?
Motivated by this, we study the distribution of singular values of the Jacobian of the generator in Generative Adversarial Networks (GANs).
Skill Rating for Generative Models
We explore a new way to evaluate generative models using insights from evaluation of competitive games between human players.
Unrestricted Adversarial Examples
We introduce a two-player contest for evaluating the safety and robustness of machine learning systems, with a large prize pool.
Discriminator Rejection Sampling
We propose a rejection sampling scheme using the discriminator of a GAN to approximately correct errors in the GAN generator distribution.
Dota 2 with Large Scale Deep Reinforcement Learning
On April 13th, 2019, OpenAI Five became the first AI system to defeat the world champions at an esports game.
A General Language Assistant as a Laboratory for Alignment
We find that the benefits from modest interventions increase with model size, generalize to a variety of alignment evaluations, and do not compromise the performance of large models.
Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
We apply preference modeling and reinforcement learning from human feedback (RLHF) to finetune language models to act as helpful and harmless assistants.
Scaling Laws and Interpretability of Learning from Repeated Data
To do this, we train a family of models where most of the data is unique but a small fraction of it is repeated many times.
Language Models (Mostly) Know What They Know
We study whether language models can evaluate the validity of their own claims and predict which questions they will be able to answer correctly.
Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned
We provide our own analysis of the data and find a variety of harmful outputs, which range from offensive language to more subtly harmful non-violent unethical outputs.
Toy Models of Superposition
Neural networks often pack many unrelated concepts into a single neuron - a puzzling phenomenon known as 'polysemanticity' which makes interpretability much more challenging.
In-context Learning and Induction Heads
In this work, we present preliminary and indirect evidence for a hypothesis that induction heads might constitute the mechanism for the majority of all "in-context learning" in large transformer models (i. e. decreasing loss at increasing token indices).
Constitutional AI: Harmlessness from AI Feedback
In the RL phase, we sample from the finetuned model, use a model to evaluate which of the two samples is better, and then train a preference model from this dataset of AI preferences.
Discovering Language Model Behaviors with Model-Written Evaluations
We also find some of the first examples of inverse scaling in RL from Human Feedback (RLHF), where more RLHF makes LMs worse.
The Capacity for Moral Self-Correction in Large Language Models
We believe that at this level of scale, language models obtain two capabilities that they can use for moral self-correction: (1) they can follow instructions and (2) they can learn complex normative concepts of harm like stereotyping, bias, and discrimination.
Specific versus General Principles for Constitutional AI
Constitutional AI offers an alternative, replacing human feedback with feedback from AI models conditioned only on a list of written principles.
