The False Promise of Imitating Proprietary LLMs
An emerging method to cheaply improve a weaker language model is to finetune it on outputs from a stronger model, such as a proprietary system like ChatGPT (e.g., Alpaca, Self-Instruct, and others). This approach looks to cheaply imitate the proprietary model's capabilities using a weaker open-...
Saved in:
Main Authors | , , , , , , , |
---|---|
Format | Journal Article |
Language | English |
Published |
25.05.2023
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | An emerging method to cheaply improve a weaker language model is to finetune
it on outputs from a stronger model, such as a proprietary system like ChatGPT
(e.g., Alpaca, Self-Instruct, and others). This approach looks to cheaply
imitate the proprietary model's capabilities using a weaker open-source model.
In this work, we critically analyze this approach. We first finetune a series
of LMs that imitate ChatGPT using varying base model sizes (1.5B--13B), data
sources, and imitation data amounts (0.3M--150M tokens). We then evaluate the
models using crowd raters and canonical NLP benchmarks. Initially, we were
surprised by the output quality of our imitation models -- they appear far
better at following instructions, and crowd workers rate their outputs as
competitive with ChatGPT. However, when conducting more targeted automatic
evaluations, we find that imitation models close little to none of the gap from
the base LM to ChatGPT on tasks that are not heavily supported in the imitation
data. We show that these performance discrepancies may slip past human raters
because imitation models are adept at mimicking ChatGPT's style but not its
factuality. Overall, we conclude that model imitation is a false promise: there
exists a substantial capabilities gap between open and closed LMs that, with
current methods, can only be bridged using an unwieldy amount of imitation data
or by using more capable base LMs. In turn, we argue that the highest leverage
action for improving open-source models is to tackle the difficult challenge of
developing better base LMs, rather than taking the shortcut of imitating
proprietary systems. |
---|---|
DOI: | 10.48550/arxiv.2305.15717 |