Abstract:

When people comprehend, interpret, or communicate about their environment, they draw on “mental schemata” that encode common knowledge and associations based on experiences, moral values, or beliefs.

New information that aligns with existing mental schemata is much more readily understood and accepted. This talk will present two projects that explore the manifestation of media framing, and moral understanding in humans in LLMs. First, / will introduce “narrative media framing,” a conceptualization of framing grounded in the social sciences that links media framing devices with cognitively salient narrative representations. Secondly, I will present our recent work where we propose a robust method for probing representations of morality in LLMs through word associations.

Bio:

Lea is a senior lecturer and DECRA fellow at the University of Melbourne. Her research aims to understand how humans learn about and represent complex information and to enable models to do the same in fair and robust ways. To achieve this goal, she combines natural language processing and machine learning with cognitive and social sciences. Recent projects include models of meaning change; common sense knowledge in human and computational representations of language; and automatic story understanding in both fiction (books or movies) and the real world media narratives on issues like climate change).