Picture for Ryan Cotterell

Ryan Cotterell

ETH Zurich

The Role of $n$-gram Smoothing in the Age of Neural Networks

Add code
Mar 25, 2024
Viaarxiv icon

Towards Explainability in Legal Outcome Prediction Models

Add code
Mar 25, 2024
Viaarxiv icon

NARRATE: Versatile Language Architecture for Optimal Control in Robotics

Add code
Mar 16, 2024
Viaarxiv icon

On the Challenges and Opportunities in Generative AI

Add code
Feb 28, 2024
Viaarxiv icon

A Theoretical Result on the Inductive Bias of RNN Language Models

Add code
Feb 24, 2024
Viaarxiv icon

What Changed? Converting Representational Interventions to Natural Language

Add code
Feb 17, 2024
Viaarxiv icon

MiMiC: Minimally Modified Counterfactuals in the Representation Space

Add code
Feb 16, 2024
Viaarxiv icon

Direct Preference Optimization with an Offset

Add code
Feb 16, 2024
Figure 1 for Direct Preference Optimization with an Offset
Figure 2 for Direct Preference Optimization with an Offset
Figure 3 for Direct Preference Optimization with an Offset
Figure 4 for Direct Preference Optimization with an Offset
Viaarxiv icon

Do Language Models Exhibit the Same Cognitive Biases in Problem Solving as Human Learners?

Add code
Jan 31, 2024
Viaarxiv icon

Principled Gradient-based Markov Chain Monte Carlo for Text Generation

Add code
Dec 29, 2023
Viaarxiv icon