Search Results for author:
Found 2 papers, 1 papers with code
Extracting Latent Steering Vectors from Pretrained Language Models
Experiments show that there exist steering vectors, which, when added to the hidden states of the language model, generate a target sentence nearly perfectly (> 99 BLEU) for English sentences from a variety of domains.
Discovering Useful Sentence Representations from Large Pretrained Language Models
We explore the question of whether these models can be adapted to be used as universal decoders.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
