Kavli Affiliate: Jia Liu | First 5 Authors: Zi Yin, Wei Ding, Jia Liu, , | Summary: Large Language Models (LLMs) are central to a multitude of applications but struggle with significant risks, notably in generating harmful content and biases. Drawing an analogy to the human psyche’s conflict between evolutionary survival instincts and societal norm […]
Continue.. Alignment is not sufficient to prevent large language models from generating harmful information: A psychoanalytic perspective