METEOR combines weak-to-strong distillation, iterative GPT-4 feedback, and contrastive self-training to adapt 7B-8B LLMs to a domain, with gains measured only by GPT-4 as judge.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
METEOR: Evolutionary Journey of Large Language Models from Guidance to Self-Growth
METEOR combines weak-to-strong distillation, iterative GPT-4 feedback, and contrastive self-training to adapt 7B-8B LLMs to a domain, with gains measured only by GPT-4 as judge.