Prepending each early layer's decoded sentence embedding to the next layer's input improves prompt-based sentence embeddings from decoder-only LLMs without fine-tuning.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs
Prepending each early layer's decoded sentence embedding to the next layer's input improves prompt-based sentence embeddings from decoder-only LLMs without fine-tuning.