7 citations · 14 across the 4 of their papers we have counts for
4 papers
disco: a toolkit for Distributional Control of Generative Models
Germán Kruszewski, Jos Rozen, Marc Dymetman
Pre-trained language models and other generative models have revolutionized NLP and beyond. However, these models tend to reproduce undesirable biases present in their training dat…
Aligning Language Models with Preferences through f-divergence Minimization
Dongyoung Go, Tomasz Korbak, Germán Kruszewski +3
Aligning language models with preferences can be posed as approximating a target distribution representing some desired behavior. Existing approaches differ both in the functional…
Sampling from Discrete Energy-Based Models with Quality/Efficiency Trade-offs
Bryan Eikema, Germán Kruszewski, Hady Elsahar +1
Energy-Based Models (EBMs) allow for extremely flexible specifications of probability distributions. However, they do not provide a mechanism for obtaining exact samples from these…
Log-Linear RNNs: Towards Recurrent Neural Networks with Flexible Prior Knowledge
Marc Dymetman, Chunyang Xiao
We introduce LL-RNNs (Log-Linear RNNs), an extension of Recurrent Neural Networks that replaces the softmax output layer by a log-linear output layer, of which the softmax is a spe…