Towards Making Text Generation Factual


Large language models like GPT-3 make it possible to turn all natural language processing tasks into text generation problems. As we move towards this paradigm of NLP in scientific and biomedical applications we need to consider whether these models are safe enough to guarantee the factuality of their outputs. Currently, they are not. But what is factuality? Are humans factual? Is science factual? This talk presents initial conceptual work on how we might teach text generation models to be (more) factual using models of how humans and institutions ensure factuality.

Dec 15, 2022 3:00 PM — 4:00 PM
QSS talks
Rowe 3089
6100 University Ave, Halifax, NS B3H 4R2