5 papers
Contrastive Decoding for Synthetic Data Generation in Low-Resource Language Modeling
Jannek Ulm, Kevin Du, Vésteinn Snæbjarnarson
Large language models (LLMs) are trained on huge amounts of textual data, and concerns have been raised that the limits of such data may soon be reached. A potential solution is to…
Discriminative Class Tokens for Text-to-Image Diffusion Models
Idan Schwartz, Vésteinn Snæbjarnarson, Hila Chefer +4
Recent advances in text-to-image diffusion models have enabled the generation of diverse and high-quality images. While impressive, the images often fall short of depicting subtle…
LoQT: Low-Rank Adapters for Quantized Pretraining
Sebastian Loeschcke, Mads Toftrup, Michael J. Kastoryano +2
Despite advances using low-rank adapters and quantization, pretraining of large models on consumer hardware has not been possible without model sharding, offloading during training…
Activation Scaling for Steering and Interpreting Language Models
Niklas Stoehr, Kevin Du, Vésteinn Snæbjarnarson +3
Given the prompt "Rome is in", can we steer a language model to flip its prediction of an incorrect token "France" to a correct token "Italy" by only multiplying a few relevant act…
Context versus Prior Knowledge in Language Models
Kevin Du, Vésteinn Snæbjarnarson, Niklas Stoehr +3
To answer a question, language models often need to integrate prior knowledge learned during pretraining and new information presented in context. We hypothesize that models perfor…