Controlled ablations of 38 models find MLM superior to CLM on representation benchmarks while CLM offers better data efficiency and stability; a biphasic CLM-then-MLM schedule is optimal under fixed compute and improves when initialized from pretrained CLM models.
Llm2vec: Large language models are secretly powerful text encoders
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
Should We Still Pretrain Encoders with Masked Language Modeling?
Controlled ablations of 38 models find MLM superior to CLM on representation benchmarks while CLM offers better data efficiency and stability; a biphasic CLM-then-MLM schedule is optimal under fixed compute and improves when initialized from pretrained CLM models.