embedding-optimization

This paper studies the problem of recovering input token sequences from last-layer hidden states of decoder-only language models using continuous embedding-space optimization, revealing that high-frequency function words are the main failure points while content words recover almost perfectly, achieving up to 97.5% exact-match rate.

This paper proposes a method to improve in-context learning by optimizing the continuous embeddings of a fixed few-shot prompt at test time, using a self-supervised confidence proxy derived from the model's log-probabilities without requiring fine-tuning or token generation.