![Editing Models with Task Arithmetic](https://pbcdn1.podbean.com/imglogo/image-logo/12375367/papers_read_ai_300x300.png)
Changing how pre-trained models behave—e.g., improving their performance on a downstream task or mitigating biases learned during pre-training—is a common practice when developing machine learning systems. In this work, we propose a new paradigm for steering the behavior of neural networks, centered around task vectors. 2022: Gabriel Ilharco, Marco Tulio Ribeiro, Mitchell Wortsman, Suchin Gururangan, Ludwig Schmidt, Hannaneh Hajishirzi, Ali Farhadi https://arxiv.org/pdf/2212.04089v1.pdf
Version: 20240320
Comments (0)
To leave or reply to comments, please download free Podbean or
No Comments
To leave or reply to comments,
please download free Podbean App.