Breaking Free Transformer Models: Task-specific Context Attribution Promises Improved Generalizability Without Fine-tuning Pre-trained LLMs

1 code implementation • 30 Jan 2024 • Stepan Tytarenko, Mohammad Ruhul Amin

We show that a linear transformation of the text representation from any transformer model using the task-specific concept operator results in a projection onto the latent concept space, referred to as context attribution in this paper.

Sentiment Analysis Sentiment Classification +3