University of Cambridge > Talks.cam > Language Technology Lab Seminars > Inverting Language Models

  Browse A-Z

Log in

Googledetails Microsoftdetails

🔐 Log In

Information on

Subscribing to talksdetails Finding a talkdetails Adding a talkdetails Disseminating talksdetails Help and Documentationdetails

ℹī¸ Information

Inverting Language Models

Download to your calendar using vCal

If you have a question about this talk, please contact Panagiotis Fytas .

As language models enter production environments, their intermediate states are used for a myriad of downstream applications such as search, prompting, and document comparison. In this talk, I discuss the feasibility of language model inversion. Specifically, we are interested in how much information language models contain about their inputs? We investigate the problem in two scenarios, recovering text inputs from the outputs of embeddings from sentence embedders and next-token probability outputs from language models. In many cases, our methods are able to fully recover exact textual inputs given just intermediate states. I’ll discuss the security implications of these findings, as well as what this tells us about compression embedding and language modeling applications.

This talk is part of the Language Technology Lab Seminars series.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

4.30-6.00 Donald McIntyre Building, Faculty of Education, 184 Hills Road, Cambridge, room GS1 MRC LMB: Klug Seminar Room 2A180 Mind-matter Unification Project (TCM Group, Cavendish Laboratory)

Other talks

The Inaccessible Game TBC Organiser's Welcome Alicia Anderson discussing some exciting news about HARPS3 Haematology and Palliative Care Title to be confirmed
 

Š 2006-2025 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity