5 papers · 1 filter
Approximating Language Model Training Data from Weights
John X. Morris, Junjie Oscar Yin, Woojeong Kim +2
Modern language models often have open weights but closed training data. We formalize the problem of data approximation from model weights and propose several baselines and metrics…
How much do language models memorize?
John X. Morris, Chawin Sitawarin, Chuan Guo +5
We propose a new method for estimating how much a model knows about a datapoint and use it to measure the capacity of modern language models. Prior studies of language model memori…
Universal Zero-shot Embedding Inversion
Collin Zhang, John X. Morris, Vitaly Shmatikov
Embedding inversion, i.e., reconstructing text given its embedding and black-box access to the embedding encoder, is a fundamental problem in both NLP and security. From the NLP pe…
Contextual Document Embeddings
John X. Morris, Alexander M. Rush
Dense document embeddings are central to neural retrieval. The dominant paradigm is to train and construct embeddings by running encoders directly on individual documents. In this…
Extracting Prompts by Inverting LLM Outputs
Collin Zhang, John X. Morris, Vitaly Shmatikov
We consider the problem of language model inversion: given outputs of a language model, we seek to extract the prompt that generated these outputs. We develop a new black-box metho…