Learning by Distilling Context
Language models significantly benefit from context tokens, such as prompts or scratchpads. They perform better when prompted with informative instructions, and they acquire new reasoning capabilities by generating a scratch-pad before predicting the final answers. However, they do not \textit{intern...
Saved in:
Main Authors | , , |
---|---|
Format | Journal Article |
Language | English |
Published |
29.09.2022
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | Language models significantly benefit from context tokens, such as prompts or
scratchpads. They perform better when prompted with informative instructions,
and they acquire new reasoning capabilities by generating a scratch-pad before
predicting the final answers. However, they do not \textit{internalize} these
performance gains, which disappear when the context tokens are gone. Our work
proposes to apply context distillation so that a language model can improve
itself by internalizing these gains. Concretely, given a synthetic unlabeled
input for the target task, we condition the model on ``[instructions] +
[task-input]'' to predict ``[scratch-pad] + [final answer]''; then we fine-tune
the same model to predict its own ``[final answer]'' conditioned on the
``[task-input]'', without seeing the ``[instructions]'' or using the
``[scratch-pad]''.
We show that context distillation is a general method to train language
models, and it can effectively internalize 3 types of training signals. First,
it can internalize abstract task instructions and explanations, so we can
iteratively update the model parameters with new instructions and overwrite old
ones. Second, it can internalize step-by-step reasoning for complex tasks
(e.g., 8-digit addition), and such a newly acquired capability proves to be
useful for other downstream tasks. Finally, it can internalize concrete
training examples, and it outperforms directly learning with gradient descent
by 9\% on the SPIDER Text-to-SQL dataset; furthermore, combining context
distillation operations can internalize more training examples than the context
window size allows. |
---|---|
DOI: | 10.48550/arxiv.2209.15189 |