Language models produce a distribution over the next token; can we use this information to recover the prompt tokens? We consider the problem of language model inversion and show that next-token probabilities contain a surprising amount of information about the preceding text. Often we can recover the text in cases where it is hidden from the user, motivating a method for recovering unknown prompts given only the model's current distribution output. We consider a variety of model access scenarios, and show how even without predictions for every token in the vocabulary we can recover the probability vector through search. On Llama-2 7b, our inversion method reconstructs prompts with a BLEU of 59 and token-level F1 of 78 and recovers 27% of prompts exactly. Code for reproducing all experiments is available at http://github.com/jxmorris12/vec2text.
@article{arxiv.2311.13647,
title = {Language Model Inversion},
author = {John X. Morris and Wenting Zhao and Justin T. Chiu and Vitaly Shmatikov and Alexander M. Rush},
journal= {arXiv preprint arXiv:2311.13647},
year = {2023}
}