Repeated motifs collapse pseudo-perplexity to near one in transformer protein language models because the model retrieves the masked residue from the duplicate copy, a behavior that can distort fitness rankings.
Rna language models predict mutations that improve rna function,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
In-Context Learning can distort the relationship between sequence likelihoods and biological fitness
Repeated motifs collapse pseudo-perplexity to near one in transformer protein language models because the model retrieves the masked residue from the duplicate copy, a behavior that can distort fitness rankings.