Search Results for author:
Found 12 papers, 8 papers with code
Connecting the Dots: LLMs can Infer and Verbalize Latent Structure from Disparate Training Data
As a step towards answering this question, we study inductive out-of-context reasoning (OOCR), a type of generalization in which LLMs infer latent information from evidence distributed across training documents and apply it to downstream tasks without in-context learning.
Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training
We find that such backdoor behavior can be made persistent, so that it is not removed by standard safety training techniques, including supervised fine-tuning, reinforcement learning, and adversarial training (eliciting unsafe behavior and then training to remove it).
Studying Large Language Model Generalization with Influence Functions
When trying to gain better visibility into a machine learning model in order to understand and mitigate the associated risks, a potentially valuable source of evidence is: which training examples most contribute to a given behavior?
Path Independent Equilibrium Models Can Better Exploit Test-Time Computation
Designing networks capable of attaining better performance with an increased inference budget is important to facilitate generalization to harder problem instances.
Exploring Length Generalization in Large Language Models
The ability to extrapolate from short problem instances to longer ones is an important form of out-of-distribution generalization in reasoning tasks, and is crucial when learning from datasets where longer problem instances are rare.
Solving Quantitative Reasoning Problems with Language Models
Language models have achieved remarkable performance on a wide range of tasks that require natural language understanding.
Ranked #13 on
Math Word Problem Solving
on MATH
Learning to Give Checkable Answers with Prover-Verifier Games
We develop instantiations of the PVG for two algorithmic tasks, and show that in practice, the verifier learns a robust decision rule that is able to receive useful and reliable information from an untrusted prover.
Learning to Elect
Voting systems have a wide range of applications including recommender systems, web search, product design and elections.
Preventing Gradient Attenuation in Lipschitz Constrained Convolutional Networks
Our BCOP parameterization allows us to train large convolutional networks with provable Lipschitz bounds.
TimbreTron: A WaveNet(CycleGAN(CQT(Audio))) Pipeline for Musical Timbre Transfer
In this work, we address the problem of musical timbre transfer, where the goal is to manipulate the timbre of a sound sample from one instrument to match another instrument while preserving other musical content, such as pitch, rhythm, and loudness.
Sorting out Lipschitz function approximation
We identify a necessary property for such an architecture: each of the layers must preserve the gradient norm during backpropagation.
Training Deep Networks with Synthetic Data: Bridging the Reality Gap by Domain Randomization
We present a system for training deep neural networks for object detection using synthetic images.
