The seminar hosted on Friday 30th June will welcome Jacob Andreas. Jacob Andreas is the X Consortium Assistant Professor at MIT. His research aims to build intelligent systems that can communicate effectively using language and learn from human guidance. Jacob earned his Ph.D. from UC Berkeley, his M.Phil. from Cambridge (where he studied as a Churchill scholar) and his B.S. from Columbia. He has been named a National Academy of Sciences Kavli Fellow, and has received the NSF CAREER award, MIT's Junior Bose and Kolokotrones teaching awards, and paper awards at NAACL and ICML. Abstract: The extent to which language modeling induces representations of the world outside text—and the broader question of whether it is possible to learn about meaning from text alone—have remained a subject of ongoing debate across NLP and cognitive sciences. I'll present two studies from my lab showing that transformer language models encode structured and manipulable models of situations in their hidden representations. I'll begin by presenting evidence from *semantic probing* indicating that LM representations of entity mentions encode information about entities' dynamic state, and that these state representations are causally implicated downstream language generation. Despite this, even today's largest LMs are prone to glaring semantic errors: they hallucinate facts, contradict input text, or even their own previous outputs. Building on our understanding of how LMs build models of entities and events, I'll present a *representation editing* model called REMEDI that can correct these errors directly in an LM's representation space, in some cases making it possible to generate output that cannot be produced with a corresponding textual prompt, and to detect incorrect or incoherent output before it is generated. Please join us online following below link This article was published on 2024-11-22
