In high-dimensional analysis, pretrained PCA representations for linear probing generalize best at low dimensionality when pretraining data is plentiful but labeled data scarce, with an exact trade-off showing how much unlabeled data replaces one labeled sample.
LoRA: Low-rank adaptation of large language models
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Transformer models detect applicant gender in de-gendered academic recommendation letters via implicit linguistic patterns such as associations with words like 'emotional' and 'humanitarian', and removing these cues reduces but does not eliminate prediction accuracy above chance.
citing papers explorer
-
Optimal Representation Size: High-Dimensional Analysis of Pretraining and Linear Probing
In high-dimensional analysis, pretrained PCA representations for linear probing generalize best at low dimensionality when pretraining data is plentiful but labeled data scarce, with an exact trade-off showing how much unlabeled data replaces one labeled sample.
-
Identifying and Mitigating Gender Cues in Academic Recommendation Letters: An Interpretability Case Study
Transformer models detect applicant gender in de-gendered academic recommendation letters via implicit linguistic patterns such as associations with words like 'emotional' and 'humanitarian', and removing these cues reduces but does not eliminate prediction accuracy above chance.