Alignment performance plateaus quickly with data, and a GMM-plus-entropy sampling method (ISA) can allegedly match full-dataset alignment with under 10% of the data, though the supporting evidence is weak.
Hello dolly: Democratizing the magic of chat- gpt with open models, 2023
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
-
Efficient Alignment of Large Language Models via Data Sampling
Alignment performance plateaus quickly with data, and a GMM-plus-entropy sampling method (ISA) can allegedly match full-dataset alignment with under 10% of the data, though the supporting evidence is weak.