← Search

Nivedita Suresh

1 accepted papers

2022

Extracting Latent Steering Vectors from Pretrained Language Models

ACL 2022findings

Prior work on controllable text generation has focused on learning how to control language models through trainable decoding, smart-prompt design, or fine-tuning based on a desired objective. We hypothesize that the information needed to steer the model to generate a target sentence is already encod…