A GPT-2 model fine-tuned on multilingual sentence similarity achieves at best 81% accuracy on classifying matching vs non-matching DNA-protein pairs, but the result is highly seed-dependent and only with an easy test set.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
q-bio.GN 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Find Central Dogma Again: Leveraging Multilingual Transfer in Large Language Models
A GPT-2 model fine-tuned on multilingual sentence similarity achieves at best 81% accuracy on classifying matching vs non-matching DNA-protein pairs, but the result is highly seed-dependent and only with an easy test set.