Daily Paper Cast podcast

Weight-Space Programming Doesn't Need Transformers

0:00
21:22
15 Sekunden vorwärts
15 Sekunden vorwärts

🤗 Upvotes: 40 | cs.LG, cs.AI, cs.CL

Authors:
Hyunjong Ok, Jaeho Lee

Title:
Weight-Space Programming Doesn't Need Transformers

Arxiv:
http://arxiv.org/abs/2611.22055v1

Abstract:
Standard neural architectures such as the Transformer were chosen because they train well with gradient descent and run fast on GPUs. In weight-space programming, a large language model (LLM) writes target weights by hand without gradient-based training, so those reasons no longer apply. Should we keep the Transformer? Given minimal guidance, ten labeled examples, and a sandbox, mainly on multiple-choice questions, we task three frontier LLMs with either generating the weights of a fixed architecture or designing the architecture themselves. When free to design, all three compile plain-text facts into a sparse table queried by a fixed procedure, reaching up to 54.4% test accuracy. An LLM-designed model achieves higher test accuracy than the most accurate released Transformer that the same LLM wrote while using about 1,800x fewer parameters. Without gradients, they choose a table, in which the LLM can state what each weight means and can find and rewrite a wrong one. Each wrong answer points to one row, and removing a row changes about one other answer. From this, we propose an associative-memory-based model up to 17x faster on GPUs than a same-sized Transformer. We also test pretrained weights, other benchmarks, and tasks where models generate answers. Pretrained LLMs remain more accurate; the claim concerns which structure to build when writing weights.

Weitere Episoden von „Daily Paper Cast“