Summary
Pseudoperplexity is somewhat predictive of the accuracy of stability predictions made from protein language model representations. Stability probes perform better on sequences assigned higher likelihood by ESMC, making pseudoperplexity a useful indicator of whether the model represents a sequence reliably (1).
See also
- Sequences with lower log-likelihoods are worse for zero-shot variant effect prediction using PLMs
- Protein language models have an implicit understanding of the uncertainty of their predictions
1.
Candido S, Hayes T, Derry A, Rao R, Lin Z, Verkuil R, et al. Language Modeling Materializes a World Model of Protein Biology. 2026 Jun; Available from: http://dx.doi.org/10.64898/2026.06.03.729735