On SuperNI and TÜLU benchmarks, LoRA and adapters match full fine-tuning on average only with large ranks and optimal learning rates, while underperforming on reasoning, coding, and long-form tasks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Parameter Efficient Instruction Tuning: An Empirical Study
On SuperNI and TÜLU benchmarks, LoRA and adapters match full fine-tuning on average only with large ranks and optimal learning rates, while underperforming on reasoning, coding, and long-form tasks.