Synthetic Semantic Supervision for Contrastive Code Representation Learning in Small Transformers: An Empirical Study
Synthetic semantic supervision yields statistically significant gains over pretraining baselines of the same inference-time size on five of eight tasks, with parity on two more; once fine-tuned, it matches or exceeds zero-shot models two orders of magnitude larger on classification, and it stays on par with execution-a...
K. Paulsen, Florian Tambon, Mike Papadakis et al.
· 0 citations