Fighting Fake 'Facts' With Two Little Words

Inspired by journalists, Hopkins researchers discover a new technique to ground a large language model's answers in reality

Get the Story

Upcoming Seminars

Sep
29
Fri
12:00 pm CLSP Student Seminar – Zhengping... @ Hackerman Hall B17
CLSP Student Seminar – Zhengping... @ Hackerman Hall B17
Sep 29 @ 12:00 pm – 1:15 pm
Abstract Any valuable NLP dataset has traditionally been shipped with crowdsourced categorical labels. Instructions for collecting these labels are easy to communicate and the labels themselves are easy to annotate. However, as self-supervision based methods[...]

Center for Language and Speech Processing