Memorizing Transformers

Memorizing Transformers.
Language models typically need to be trained or finetuned in order to acquire
new knowledge, which involves updating their weights. We instead envision
language models that can simply read and memorize new data at inference time,
thus acquiring new knowledge immediately. In this work, we extend language
models with the ability to memorize the internal representations of past
inputs. We demonstrate that an approximate kNN lookup into a non-differentiable
memory of recent (key, value) pairs improves language modeling across various
benchmarks and tasks, including generic webtext (C4), math papers (arXiv),
books (PG-19), code (Github), as well as formal theorems (Isabelle). We show
that the performance steadily improves when we increase the size of memory up
to 262K tokens. On benchmarks including code and mathematics, we find that the
model is capable of making use of newly defined functions and theorems during
test time.

Read in full here:

This thread was posted by one of our members via one of our news source trackers.

Corresponding tweet for this thread:

Share link for this tweet.