Finetuning open LMs on ChatGPT outputs creates models that mimic style and fool human raters but fail to close the performance gap to proprietary systems on tasks not well-represented in the imitation data.
What neural networks memorize and why:
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2023 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
The False Promise of Imitating Proprietary LLMs
Finetuning open LMs on ChatGPT outputs creates models that mimic style and fool human raters but fail to close the performance gap to proprietary systems on tasks not well-represented in the imitation data.