This talk is part of the NLP Seminar Series.

Inverting Language Models

Jack Morris, Cornell University
Date: 11:00am - 12:00pm, August 1st 2024
Venue: Room 287, Gates Computer Science Building

Abstract

How much information do the outputs of NLP 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 both cases, our methods are able to fully recover some inputs given just the model output.

Bio

Jack Morris is a fourth-year CS PhD candidate at Cornell University and a visiting researcher with FAIR at Meta. His research spans the intersection of natural language processing, machine learning, and security, with a recent focus on applications of information retrieval systems. His research is supported by an NSF Graduate Research Fellowship.